# Skills for Agents Source: https://www.vozo.ai/docs/ai-agent/skill Use your AI agent to create, manage, and download Vozo video localization projects with natural-language prompts. Vozo Skills let you ask your AI agent to handle video localization in Vozo using natural language. They work through Vozo CLI, which is installed during setup and connects your agent to Vozo so it can create projects, check progress, and download finished files for you—without requiring you to learn or run any commands. ## What You Can Do Vozo Skills support four core localization tasks: * **AI Dubbing**: Translate speech and create dubbed video or audio in another language. * **Translate Subtitles**: Create translated subtitles or replace subtitles already visible in a video. * **Visual Translate**: Translate on-screen text while preserving its visual presentation. * **Lip Sync**: Match mouth movements to new or translated audio. You can also ask your agent to: * Process a local file, a folder of files, or a supported video URL * Create several language versions or process multiple files in a batch * Apply several Vozo tools as one workflow * Check project status and find existing projects * Export and download available videos, audio, and subtitle files ## Before You Start You need: * A Vozo account * An AI agent that can use tools and files on your computer Vozo Skills have been tested with Claude Code, Codex, OpenClaw, Cursor, WorkBuddy, and Hermes. Other AI agents that can run local tools may also work. Projects created through Vozo Skills use the same Vozo account and [points system](/docs/common/tools-points-rules) as projects created in the Vozo web app. Before creating a project, your agent shows the estimated points and asks you to confirm. ## Install Vozo Skills The easiest way to get started is to copy the prompt below into your AI agent: ```text wrap theme={null} Install vozoai/cli: https://raw.githubusercontent.com/vozoai/cli/main/installation-guide.md ``` Your agent will run the setup and tell you if it needs permission to use local tools. During sign-in, Vozo opens a secure browser page. Complete the login there, then return to your agent so it can verify your account. If you prefer to run the setup yourself, open a terminal and enter: ```bash theme={null} npx @vozoai/cli@latest install ``` After installation, return to your AI agent and ask it to sign you in to Vozo. ## Create Your First Project Give your agent a local file, a folder, or a supported video URL. Make sure the agent can access the source on your computer. Name the target language and the tasks to include, such as dubbing, subtitles, on-screen text translation, or lip sync. You can also describe preferred terminology, tone, and where to save the finished files. Check the source, target language, selected tasks, and estimated points. Confirm only when the plan matches your request. Your agent creates the project, checks its progress, and starts an export when one is required. You can continue asking for status updates while it works. When processing is complete, your agent can download the available files to a location you choose. It can also give you a link to open the project in the Vozo web app. ## Prompt Examples Use natural language and include the source, target language, and the result you want. ### Localize One Video ```text wrap theme={null} Translate this video into Spanish with dubbing and translated subtitles. Keep product names in English, and save the finished video in my Downloads folder. ``` ### Process a Folder ```text wrap theme={null} Translate every video in this folder into Japanese. Include dubbing, on-screen text translation, and lip sync, then save all finished videos in a new folder. ``` ### Create Several Language Versions ```text wrap theme={null} Make English, French, and Spanish versions of this video with dubbing and subtitles. Show me the plan and estimated points before creating anything. ``` ### Collect Completed Work ```text wrap theme={null} Find my completed Vozo projects from last week and download the available final videos and subtitle files. ``` ## Review and Edit in Vozo Projects created through Vozo Skills also appear in your Vozo account. Ask your agent to open a project when you want to review it in the Vozo web app. Vozo Skills currently focus on creating projects, checking progress, exporting results, and downloading files. To edit translations, change voices, redub content, or make other detailed changes, open the project in the Vozo web editor. ## Frequently Asked Questions No. Copy the installation prompt into your AI agent, and it will check your computer and guide you through the setup. After that, you can use Vozo Skills with plain-language requests. No. Vozo Skills help your agent run supported workflows and repetitive tasks. Use the web app when you want to visually review a project or edit its content in detail. They appear in the same Vozo account you used during sign-in. You can ask your agent to find or open a project, or browse your projects in the Vozo web app. The Vozo web app remembers the subtitle style and position you previously used. This information is stored locally in your browser, so your AI agent cannot access it when creating a project. Projects created through an agent therefore use the default subtitle style. If subtitle appearance matters, ask your agent to create the project, then open it in the Vozo web app. Review and adjust the subtitle style and position before manually exporting and downloading the video. Some edits in the Vozo web app require additional processing, such as regenerating speech or adding subtitles. If you do not wait in the browser until processing finishes, the latest changes cannot be synced to your AI agent. Your agent may then treat the project as unchanged and download the previous version instead of exporting a new video. After editing, keep the project open in the web app and wait for processing to finish. Then ask your agent to check the project again, export the latest version, and download it. Yes. Projects follow the same points rules as projects created in the Vozo web app. Your agent shows an estimate before creation and waits for your confirmation. # Create LipSync Video Job Source: https://www.vozo.ai/docs/api_reference/endpoints/lipsync/create POST /v1/video_generation Create a lipsynced talking video # Query Job Status Source: https://www.vozo.ai/docs/api_reference/endpoints/lipsync/get GET /v1/video_generation/{task_id} Query job status # Overview Source: https://www.vozo.ai/docs/api_reference/endpoints/lipsync/overview Create LipSync Or Talking Photos ## How it works Upload your video, photo, and audio files so our servers can retrieve them. Reference your hosted assets and specify your desired mode (Standard or Precision). Use our webhook callback or poll the API with your job ID until processing is complete. Retrieve the finished talking photo or lip‑synced video from the provided URL. ## Usage Limitation: * You may have up to 10 concurrent jobs (including queued requests). * Only single‑face videos or photos are supported. * Estimated queue time: 1–120 minutes, depending on system load. * Standard Mode processing time: \~10 minutes. * Precision Mode processing time: \~20 minutes. If a video or photo contains multiple faces, only the largest detected face will be lip‑synced. ## API Error Codes | Code | Description | | ---- | ---------------------------------------------------------------- | | 5 | Invalid request parameters. | | 7 | No permission to request. | | 104 | Insufficient credits. | | 814 | Your account is not a member and is not allowed to call the API. | | 1000 | Internal Server Error. | | 1301 | Callback Challenge failed. | | 1302 | API key has been revoked. | | 1304 | API key has reached the maximum number of concurrent requests. | | 1502 | Your audio driver is either invalid or cannot be downloaded. | | 1503 | Your account is not authorized to call the API. | | 1305 | Only Studio plan is allowed. | ## Job Error Codes | Code | Description | | ----- | -------------------------------------------------------- | | 999 | Failed to download the file. | | 20403 | Not enough faces. | | 20407 | The number of face tracks is too many. | | 20408 | The image-to-video facial detection has not been passed. | | 20601 | There are no faces in the picture. | | 20602 | Unknown image format. | | 20611 | Video triggering flow limit. | | 20613 | Generate video input sensitive to images. | # Create LipSync Video Job By Reusable LipSync Model Source: https://www.vozo.ai/docs/api_reference/endpoints/reusable_lipsync/create POST /v1/reusable_lipsync_model_video_generation Create a lipsynced talking video use reusable model # Create Reusable Lipsync Model Source: https://www.vozo.ai/docs/api_reference/endpoints/reusable_lipsync/create_model POST /v1/reusable_lipsync_model Create a reusable lipsync model # Query Job Status Source: https://www.vozo.ai/docs/api_reference/endpoints/reusable_lipsync/get GET /v1/video_generation/{task_id} Query job status # Overview Source: https://www.vozo.ai/docs/api_reference/endpoints/reusable_lipsync/overview Create LipSync Or Talking Photos By Reusable LipSync Model ## Why use Reusable LipSync API? The Reusable LipSync API is an optimized version of our LipSync API, designed for developers who frequently generate lip-synced videos using the same visual reference. ### What’s Different? | Feature | LipSync API | Reusable LipSync API | | :------------------- | :---------------------------------- | :-------------------------------- | | Reference upload | Required for each request | Upload once, reuse multiple times | | Training step | Required | Not required | | Input for generation | Reference + audio | Audio only (reference reused) | | Generation speed | Standard | Much faster (no retraining) | | Cost per request | 5 points base + 5 points per minute | 5 points per minute | ## How it works Create a reusable lipsync model using previous task ID from lipsync API in precision mode. Upload your audio file so our servers can retrieve them. Reference your hosted assets and specify your desired mode (Standard or Precision). Use our webhook callback or poll the API with your job ID until processing is complete. Retrieve the finished talking photo or lip‑synced video from the provided URL. ## Usage Limitation: * You may have up to 10 concurrent jobs (including queued requests). * Estimated queue time: 1–120 minutes, depending on system load. * Processing time: \~10 minutes. If a video or photo contains multiple faces, only the largest detected face will be lip‑synced. ## Model Expiration Policy Models created via the Model Creation API have an automatic expiration mechanism based on activity. ### Rules 1. Default Expiration Period Each reusable lipsync model remains active for 3 months from its creation date or last usage. 2. Automatic Extension Every time the reusable lipsync model is used (e.g., called in a reusable lipsync api request), its expiration date is extended by another 3 months from that point in time. 3. Expiration If a reusable lipsync model is not used for 3 consecutive months, it will automatically expire and may be deleted permanently. 4. Reactivation Expired reusable lipsync models cannot be reactivated. To continue using the same configuration, you must resubmit the lipsync job and recreate reusable lipsync model through the API. ## API Error Codes | Code | Description | | ---- | ------------------------------------------------------------------------------------ | | 5 | Invalid request parameters. | | 7 | No permission to request. | | 104 | Insufficient credits. | | 814 | Your account is not a member and is not allowed to call the API. | | 1000 | Internal Server Error. | | 1301 | Callback Challenge failed. | | 1302 | API key has been revoked. | | 1304 | API key has reached the maximum number of concurrent requests. | | 1502 | Your audio driver is either invalid or cannot be downloaded. | | 1503 | Your account is not authorized to call the API. | | 1504 | Task creation is not supported in Standard mode or for tasks from previous versions. | | 1305 | Only Studio plan is allowed. | | 1506 | Model is expired. | ## Job Error Codes | Code | Description | | ----- | ---------------------------- | | 999 | Failed to download the file. | | 20611 | Video triggering flow limit. | # Create Translate & Dub Job Source: https://www.vozo.ai/docs/api_reference/endpoints/translate_dub/create POST /v1/media/translate Create a translate & dub job for video or audio media # Query Translate & Dub Job Status Source: https://www.vozo.ai/docs/api_reference/endpoints/translate_dub/get GET /v1/media/translate/{task_id} Query translate & dub job status # Overview Source: https://www.vozo.ai/docs/api_reference/endpoints/translate_dub/overview Translate & Dub Video/Audio ## Inputs & Outputs Input: * media\_url * source language & target language * \[optional] subtitle\_url or ocr\_text\_box (for more accurate speech recognition) * \[optional] glossary\_ids Glossary Pn Output: * media (video or audio) * translated subtitle\_url (SRT) ## How it works Upload your video or audio, and optional subtitle (.srt) so our servers can retrieve them. If there is on‑screen text to translate, specify a normalized OCR box (x, y, width, height) from 0–1; origin at the top‑left of the frame. Include source/target languages (e.g., en‑US → zh‑CN), speaker range if needed, and export type. Use our webhook callback or poll the API with your task ID until processing is complete. Retrieve translated video/audio and the translated subtitle (.srt) from the provided URLs. ## Usage Limitation * Only users who can create API Keys may use this API. * Studio plan is required; non‑Studio users are not allowed. * Concurrency is limited independently from LipSync; queued requests are counted. * Language code follows IETF BCP 47 standard, e.g., en‑US. ## API Error Codes | Code | Description | | ---- | ---------------------------------------------------------------- | | 5 | Invalid request parameters. | | 7 | No permission to request. | | 104 | Insufficient credits. | | 814 | Your account is not a member and is not allowed to call the API. | | 1000 | Internal Server Error. | | 1301 | Callback Challenge failed. | | 1302 | API key has been revoked. | | 1304 | API key has reached the maximum number of concurrent requests. | | 1503 | Your account is not authorized to call the API. | | 1305 | Only Studio plan is allowed. | ## Job Error Codes | Code | Description | | ----- | ------------------------------------------------------------------------- | | 10001 | Uploaded file has no video stream | | 10002 | Uploaded video has no audio stream | | 10003 | Transcoding failed | | 10004 | Failed to generate HLS output | | 10005 | Video cropping failed | | 10010 | Voice separation failed (speech vs. background) | | 10020 | Automatic speech recognition (ASR) failed | | 10021 | Multi‑speaker ASR failed | | 10022 | Speaker diarization (Chinese) failed | | 10023 | Failed to generate full subtitles | | 10030 | Translation failed | | 10031 | Mixed languages detected; aggregation failed after punctuation adjustment | | 10032 | OCR extraction failed | | 10033 | OCR language not supported | | 10034 | Subtitle (SRT) alignment failed | | 10040 | Voice cloning failed | | 10041 | No recognized speech content | | 10042 | No speech detected | | 10043 | Re‑cloning voice failed | | 10044 | Preview text for TTS is empty | | 10045 | Failed to generate preview audio | ## Supported Languages ### Source Languages Note: "auto" is supported to automatically detect the source language and update SourceLanguage when detected. | Code | Name | | ------ | -------------------------------- | | auto | Auto Detect | | en-US | English (United States) | | en-GB | English (United Kingdom) | | en-AU | English (Australia) | | en-CA | English (Canada) | | en-GH | English (Ghana) | | en-HK | English (Hong Kong) | | en-IE | English (Ireland) | | en-IN | English (India) | | en-KE | English (Kenya) | | en-NG | English (Nigeria) | | en-NZ | English (New Zealand) | | en-PH | English (Philippines) | | en-SG | English (Singapore) | | en-TZ | English (Tanzania) | | en-ZA | English (South Africa) | | zh-CN | Chinese (China, Simplified) | | zh-HK | Chinese (Hong Kong, Traditional) | | zh-TW | Chinese (Taiwan, Traditional) | | es-ES | Spanish (Spain) | | es-MX | Spanish (Mexico) | | es-US | Spanish (United States) | | es-AR | Spanish (Argentina) | | es-BO | Spanish (Bolivia) | | es-CL | Spanish (Chile) | | es-CO | Spanish (Colombia) | | es-CR | Spanish (Costa Rica) | | es-CU | Spanish (Cuba) | | es-DO | Spanish (Dominican Republic) | | es-EC | Spanish (Ecuador) | | es-GQ | Spanish (Equatorial Guinea) | | es-GT | Spanish (Guatemala) | | es-HN | Spanish (Honduras) | | es-NI | Spanish (Nicaragua) | | es-PA | Spanish (Panama) | | es-PE | Spanish (Peru) | | es-PR | Spanish (Puerto Rico) | | es-PY | Spanish (Paraguay) | | es-SV | Spanish (El Salvador) | | es-UY | Spanish (Uruguay) | | es-VE | Spanish (Venezuela) | | ar-EG | Arabic (Egypt) | | ar-SA | Arabic (Saudi Arabia) | | ar-AE | Arabic (United Arab Emirates) | | ar-MA | Arabic (Morocco) | | ar-SY | Arabic (Syria) | | ru-RU | Russian (Russia) | | pt-PT | Portuguese (Portugal) | | pt-BR | Portuguese (Brazil) | | fr-BE | French (Belgium) | | fr-CA | French (Canada) | | fr-CH | French (Switzerland) | | fr-FR | French (France) | | de-DE | German (Germany) | | de-AT | German (Austria) | | de-CH | German (Switzerland) | | ko-KR | Korean (South Korea) | | ja-JP | Japanese (Japan) | | hi-IN | Hindi (India) | | tr-TR | Turkish (Turkey) | | ur-IN | Urdu (India) | | fil-PH | Filipino (Philippines) | | fi-FI | Finnish (Finland) | | cs-CZ | Czech (Czech Republic) | | hu-HU | Hungarian (Hungary) | | da-DK | Danish (Denmark) | | nl-BE | Dutch (Belgium) | | pl-PL | Polish (Poland) | | ro-RO | Romanian (Romania) | | sk-SK | Slovak (Slovakia) | | sv-SE | Swedish (Sweden) | | hr-HR | Croatian (Croatia) | | id-ID | Indonesian (Indonesia) | | it-IT | Italian (Italy) | | it-CH | Italian (Switzerland) | | bg-BG | Bulgarian (Bulgaria) | | el-GR | Greek (Greece) | | ms-MY | Malay (Malaysia) | | ta-IN | Tamil (India) | | uk-UA | Ukrainian (Ukraine) | | sq-AL | Albanian (Albania) | | az-AZ | Azerbaijani (Azerbaijan) | | eu-ES | Basque (Spain) | | bn-IN | Bengali (India) | | bs-BA | Bosnian (Bosnia and Herzegovina) | | yue-CN | Cantonese (China) | | ca-ES | Catalan (Spain) | | gl-ES | Galician (Spain) | | gu-IN | Gujarati (India) | | is-IS | Icelandic (Iceland) | | kn-IN | Kannada (India) | | kk-KZ | Kazakh (Kazakhstan) | | lv-LV | Latvian (Latvia) | | lt-LT | Lithuanian (Lithuania) | | mk-MK | Macedonian (North Macedonia) | | ml-IN | Malayalam (India) | | mt-MT | Maltese (Malta) | | mr-IN | Marathi (India) | | mn-MN | Mongolian (Mongolia) | | ne-NP | Nepali (Nepal) | | nb-NO | Norwegian Bokmål (Norway) | | pa-IN | Punjabi (India) | | sl-SI | Slovenian (Slovenia) | | so-SO | Somali (Somalia) | | sr-RS | Serbian (Serbia) | | sw-KE | Swahili (Kenya) | | sw-TZ | Swahili (Tanzania) | | uz-UZ | Uzbek (Uzbekistan) | | vi-VN | Vietnamese (Vietnam) | | he-IL | Hebrew (Israel) | | fa-IR | Persian (Iran) | | th-TH | Thai (Thailand) | ### Target Languages | Code | Name | Locale variants | | ---- | ---------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- | | en | English | en‑US, en‑GB, en‑AU, en‑CA, en‑HK, en‑KE, en‑NZ, en‑NG, en‑PH, en‑SG, en‑ZA, en‑TZ | | zh | Chinese | zh‑CN, zh‑HK, zh‑TW, zh‑CN‑shandong, zh‑CN‑liaoning, zh‑CN‑sichuan, zh‑CN‑henan, zh‑CN‑shaanxi, zh‑CN‑GUANGXI | | wuu | Wu Chinese | wuu‑CN | | es | Spanish | es‑ES, es‑MX, es‑US, es‑AR, es‑BO, es‑CL, es‑CO, es‑CR, es‑CU, es‑DO, es‑EC, es‑SV, es‑GQ, es‑GT, es‑HN, es‑NI, es‑PA, es‑PY, es‑PE, es‑PR, es‑UY, es‑VE | | ar | Arabic | ar‑DZ, ar‑BH, ar‑IQ, ar‑JO, ar‑KW, ar‑LB, ar‑LY, ar‑MA, ar‑OM, ar‑QA, ar‑SY, ar‑TN, ar‑AE, ar‑YE | | ru | Russian | ru‑RU | | pt | Portuguese | pt‑PT, pt‑BR | | fr | French | fr‑FR, fr‑CA, fr‑BE, fr‑CH | | de | German | de‑DE, de‑AT, de‑CH | | ko | Korean | ko‑KR | | ja | Japanese | ja‑JP | | hi | Hindi | hi‑IN | | tr | Turkish | tr‑TR | | fil | Filipino | fil‑PH | | fi | Finnish | fi‑FI | | cs | Czech | cs‑CZ | | da | Danish | da‑DK | | nl | Dutch | nl‑BE | | pl | Polish | pl‑PL | | ro | Romanian | ro‑RO | | sk | Slovak | sk‑SK | | sv | Swedish | sv‑SE | | hr | Croatian | hr‑HR | | id | Indonesian | id‑ID | | it | Italian | it‑IT, it‑CH | | bg | Bulgarian | bg‑BG | | el | Greek | el‑GR | | ms | Malay | ms‑MY | | ta | Tamil | ta‑IN, ta‑MY, ta‑SG, ta‑LK | | uk | Ukrainian | uk‑UA | | th | Thai | th‑TH | | vi | Vietnamese | vi‑VN | | am | Amharic | am‑ET | | bn | Bengali | bn‑IN, bn‑BD | | as | Assamese | as | | bs | Bosnian | bs‑BA | | ca | Catalan | ca‑ES | | et | Estonian | et‑EE | | eu | Basque | eu‑ES | | gl | Galician | gl‑ES | | gu | Gujarati | gu | | he | Hebrew | he‑IL | | hu | Hungarian | hu‑HU | | iu | Inuktitut | iu‑CANS‑CA, iu‑LATN‑CA | | jv | Javanese | jv‑ID | | mk | Macedonian | mk‑MK | | mr | Marathi | mr | | nb | Norwegian Bokmål | nb‑NO | | ne | Nepali | ne‑NP | | or | Oriya | or | | pa | Punjabi | pa | | ps | Pashto | ps‑AF | | sl | Slovenian | sl‑SI | | sw | Swahili | sw‑KE, sw‑TZ | | te | Telugu | te‑IN | | ur | Urdu | ur, ur‑IN, ur‑PK | | zu | Zulu | zu‑ZA | # Create Visual Translate Job Source: https://www.vozo.ai/docs/api_reference/endpoints/visual_translate/create POST /v1/media/frame_translate Create a visual translation job for video on-screen text # Query Visual Translate Job Status Source: https://www.vozo.ai/docs/api_reference/endpoints/visual_translate/get GET /v1/media/frame_translate/{task_id} Query visual translation job status # Overview Source: https://www.vozo.ai/docs/api_reference/endpoints/visual_translate/overview Visual Translate API ## Inputs & Outputs Input: * video\_url * source language & target language * \[optional] glossary\_ids * \[optional] user\_prompt * \[optional] project\_mode Output: * translated video\_url * project\_url when `project_mode` is `editable` ## How it works Upload your input video so our servers can retrieve it. The video must be no longer than 20 minutes. Include the source and target language codes, and optional glossary IDs or prompt instructions for terminology and style. Use your webhook callback or poll the API with the returned task ID until processing is complete. When the job is done, retrieve the translated video from `video_url`. If you created an editable project, open `project_url` to review or edit it in the web dashboard. ## Usage Limitation * Only users who can create API Keys may use this API. * Studio plan is required; non-Studio users are not allowed. * Input must be a video file. Audio-only export is not supported. * The maximum supported input duration is 20 minutes. * Source language auto-detection is not supported. Pass a supported source language code explicitly. * Language code follows IETF BCP 47 style, e.g., `en-US`, `zh-CN`, `zh-CN-GUANGXI`. ## API Error Codes | Code | Description | | ---- | ---------------------------------------------------------------- | | 5 | Invalid request parameters. | | 7 | No permission to request. | | 104 | Insufficient credits. | | 814 | Your account is not a member and is not allowed to call the API. | | 1000 | Internal Server Error. | | 1301 | Callback Challenge failed. | | 1302 | API key has been revoked. | | 1304 | API key has reached the maximum number of concurrent requests. | | 1503 | Your account is not authorized to call the API. | | 1305 | Only Studio plan is allowed. | ## Job Error Codes | Code | Description | | ----- | ---------------------------------- | | 40002 | Uploaded file has no video stream. | | 40010 | Transcoding failed. | | 40050 | Translation failed. | | 40020 | OCR extraction failed. | | 40032 | No valid callouts in video. | | 40040 | Matching ocr to callouts failed. | | 40041 | Fail to match any callout to ocr. | | 40060 | Failed to refine callouts. | | 40061 | Failed to extract style in refine. | | 40080 | Generating preview video failed. | # Get Started Source: https://www.vozo.ai/docs/api_reference/get_started Learn about the APIs provided by Vozo, their pricing, and how to use them. If you encounter any issues, please contact [support@vozo.ai](mailto:support@vozo.ai). ## Overview The Vozo API currently supports the following APIs: 1. Translate and Dub API 2. Visual Translate API 3. LipSync API 4. Reusable LipSync API ## Pricing 1. Pricing follows the same structure as submitting jobs via the Vozo portal: [Points Usage for AI Tools](https://www.vozo.ai/docs/common/tools-points-rules) 2. Points are deducted from your account once a job completes successfully. If your balance is insufficient, subsequent API requests will fail. ## Getting the API Key 1. API access is available exclusively for users on the Studio plan and above. Please contact [bd@vozo.ai](mailto:bd@vozo.ai) to request API access. 2. After approval, you could find the "API Keys" in your profile dropdown: Api Key Pn ## Frequently Asked Questions You can check the detailed point usage for each project on the Dashboard – top right avatar → [Points Usage History](https://app.vozo.ai/points_history) – and export the data for your records. No. Priority is determined by subscription plan. If you need faster prociessing, please contact [bd@vozo.ai](mailto:bd@vozo.ai). # Glossary Source: https://www.vozo.ai/docs/common/glossary Ensure consistent translation and pronunciation of key terms with custom glossaries. Glossary is available to **Studio** and higher-tier members. ## What Is a Glossary? A **Glossary** ensures consistent translation and pronunciation of specific terms across your project. This is especially useful for: * Brand names * Industry-specific terminology * Names and proper nouns * Fixed expressions that shouldn't be translated ## Create a Glossary To create and manage glossaries: 1. On the **Dashboard**, click the **Glossaries** tab in the left sidebar. 2. You will see a list of all glossaries you’ve created, along with their language pairs and number of terms. 3. Click **New Glossary** to create a new glossary. This will open the term editor page, where you can: * Add new term pairs * Edit or delete existing terms * Import terms via CSV Glossary Pn ### Add New Term Pair To add a term manually: 1. Select the **source language** and **target language**. 2. Enter the **source term** and **target term**. Check **Do not translate** if you want to preserve the original term in the output, such as brand names. 3. (Optional) Add a pronunciation to guide dubbing output. Pronunciation only applies to Translate & Dub. 4. Click **Add Term Pair**. ### Import from CSV To import multiple terms at once from an existing glossary file: 1. Click **Import**. 2. Prepare a `.csv` file with 5 columns: * Source Term * Target Term * Source Lang Code * Target Lang Code * Pronunciation (optional) 3. **Do not include a header row**—the first row will be treated as a term pair. 4. Drag your file into the upload area or click to select it. 5. Click **Import** to upload. ## Use Glossary in a Project When creating a **Translation Project**, you can choose one or more glossaries in the **Advanced Settings** section. 1. Expand the **Advanced Settings**. 2. In the **Glossary** dropdown, select one or more glossaries. 3. The selected glossaries will guide translation. If any term conflicts exist across glossaries, terms from the glossary listed first will be used with higher priority. # Pronunciation Source: https://www.vozo.ai/docs/common/pronunciation Fix mispronounced words in the dubbed audio—like names, brands, places, or technical terms. ## How to Use Click on the sentence and select the word that sounds incorrect. Click **Pronunciation** in the toolbar. Enter the correct pronunciation, and preview the result. If the same word appears multiple times in the project and you want to update all of them with the same pronunciation, check **Apply to x instances of “x”** to apply the change across all identical words. Click **Confirm**, then **Update Dubbing** to regenerate the edited segments. ## Enter Correct Pronunciation You can follow these examples: | Original Word / Phrase | How to Enter the Pronunciation | Notes | | ---------------------- | ------------------------------ | ------------------------------------------- | | AI | A-eye | | | Vozo | Voh-zoh | | | NASA | Nassa | Read as a word, not spelled out | | YouTube | You-toob | | | Arkansas | Ar-kan-saw | Silent “s” at the end; often mispronounced | | Beyoncé | Bee-YON-say | Stress on second syllable “YON” | | GIF | Jiff or Giff | Depending on preference | | 2025 | Twenty twenty-five | Standard way to speak years | | 01:30 (time of day) | One thirty | Most natural for time of day | | 01:30 (duration) | One minute and thirty | Use when referring to length of video/audio | This only affects pronunciation and will not change the subtitles. ## Pronunciation Tips * Use phonetic spellings that mimic how the word sounds. * Use hyphens (`-`) to split syllables or highlight emphasis. * Try several versions if needed, and preview the audio to check which sounds most natural. * For abbreviations, spell out letters (e.g., F-A-Q) if they’re not being pronounced correctly. ## Chinese Pronunciation Issues For Chinese content, mispronunciations can occur due to multi-pronunciation characters or rare/unrecognized characters. We recommend using a common character with the same pronunciation to guide the speech engine. If a character is mispronounced (e.g. due to multiple possible readings), or cannot be pronounced at all (e.g. a rare character), you can substitute it with a more commonly used character that sounds the same. For example: | Original Character | How to Enter the Pronunciation | Notes | | ------------------ | ------------------------------ | ----------------------------------------------------------- | | “行” | “型” | Use to force xíng and avoid háng | | “殷” | “音” | Use to force the correct yīn pronunciation and avoid errors | ## FAQ No, this only affects pronunciation and will not change the subtitles. # Remove Original Subtitles Source: https://www.vozo.ai/docs/common/remove-original-subtitles ## Overview This feature is available in both **Translate & Dub** and **Translate Subtitles**. Once enabled, Vozo will automatically detect and remove the original subtitles in the video, and replace them with translated subtitles. The new subtitles will be placed in the same position as the original ones. You can adjust subtitle style and position in the editor. Subtitles Remove Demo How to Enable Original Subtitle Removal: * In Translate & Dub: After uploading your video, enable Add Translated Subtitles in Video, then select Add & Remove Original. * In Translate Subtitles: After uploading your video, enable Remove Original Subtitles. ## What Will Be Removed This feature removes subtitles that meet all of the following conditions: * Fixed position in the video * Simple animation * Matches the spoken content Subtitle Remove Good Videos ## What Will Not Be Removed The following types of text will not be removed: * **Text that does not match the spoken content**, such as emphasis text, titles, or name labels\ If you need to remove and translate this type of content, use [Visual Translate](https://www.vozo.ai/docs/visual_translate/get-started) * **Subtitles with changing positions or complex animations**\ If you need to remove and translate this type of content, use [Visual Translate](https://www.vozo.ai/docs/visual_translate/get-started) * **Scene text that is part of the original footage**, such as store signs, product packaging, or physical menus ## Pricing Using this feature will incur an additional cost of **1 point per minute**. # Points Usage for Speech Generation Source: https://www.vozo.ai/docs/common/speech-points-rules Understand how points are consumed when generating or regenerating speech. ## Points Rules Vozo charges points based on the length of audio generated. The pricing is as follows: | Action | Cost | | ---------------------------------- | ------------------- | | **Generate Speech** | 3 points per minute | | **Regenerate Speech (no changes)** | Free | Points are calculated based on the generated speech length, rounded to two decimal places, with a minimum charge of 0.01 points. ## When Are Points Charged? * Every time you generate speech for a segment — whether it's newly added, edited, or updated with changes such as **changed** **voice or speaker**, **added pauses**, or **pronunciation edits** — points will be deducted based on the full duration of the newly generated speech. * The rate is **3 points per minute**, and the exact cost depends on the final speech length. Example: If you edit a segment and the generated speech length is 8 seconds, the cost will be 8/60 × 3 = 0.4 points. ## When Is It Free? * If you click **Regenerate Speech** without making any changes to the segment, no points will be charged. * Adjusting **speech speed**, **volume**, or **pitch** does not consume any points. ## Exceptions The [**Enhance Emotion**](/docs/translate_dub/emotion) feature is charged differently. It costs **1 point per segment**, regardless of speech length. ## FAQ Yes. If points were deducted but the generation failed, all points will be refunded automatically. # Points Usage for AI Tools Source: https://www.vozo.ai/docs/common/tools-points-rules Learn how points are consumed when using different AI tools in Vozo. ## Translate & Dub **Cost**: 3 points per minute The cost is calculated based on the total uploaded video/audio duration. **Example**: 1-minute video = 3 × 1 (minute) = 3 points ## Translate Subtitles Translate Subtitles is currently offered as a limited-time free feature for all subscribed users and does not consume AI Points. If your usage exceeds the free allowance, click the chat button in the bottom-right corner or email [**bd@vozo.ai**](mailto:bd@vozo.ai) to contact our BD team for additional quota. ## Visual Translate **Cost**: 10 points per minute The cost is calculated based on the total uploaded video duration. **Example**: 1-minute video = 10 × 1 (minute) = 10 points ## Lip Sync **Cost**: 5 points base + 5 points per minute The cost is calculated based on the total generated video duration. [Creating a variant](/docs/lipsync/variants) within the same project only costs 5 points per minute, with no additional 5 base points. **Example**: * New project (1-minute video) = 5 (base) + 5 × 1 (minute) = **10 points** * Variant (1-minute video) = 0 (base) + 5 × 1 (minute) = **5 points** ## Talking Photo **Cost**: 5 points base + 5 points per minute The cost is calculated based on the total generated video duration. [Creating a variant](/docs/talking_photo/variants) within the same project only costs 5 points per minute, with no additional 5 base points. **Example**: * New project (1-minute video) = 5 (base) + 5 × 1 (minute) = **10 points** * Variant (1-minute video) = 0 (base) + 5 × 1 (minute) = **5 points** ## Voice Studio **Cost**: 3 points per minute Points are charged based on the length of the generated audio. **Example**: 30-second speech = 3 × 0.5 (minutes) = **1.5 points** ## Long Video to Shorts **Cost**: 1 point per 3 minutes of original video duration Charged based on the length of the uploaded long video, not the generated shorts. **Example**: 60-minute video = 60 ÷ 3 (minutes) = 20 points ## Face Swap **Cost**: 5 points base + 5 points per minute Charged based on the uploaded video duration. **Example**: 1-minute video = 5 (base) + 5 × 1 (minute) = 10 points ## FAQ AI Points follow different validity rules depending on how they are issued. Please refer to the details below.\ \ Gift AI Points (for new users):\ Gift AI Points are valid for 7 days from the date of account registration. Any unused Gift AI Points will be automatically cleared after 7 days.\ \ Monthly Subscriptions:\ AI Points are issued each month after successful billing.\ Each monthly allocation is valid for 2 months, meaning that unused AI Points are automatically carried over to the next month.\ Example: * 100 AI Points issued on January 1 will expire on March 1. * You’ll also receive 100 AI Points for February on February 1, which will expire on April 1. \ Annual Subscriptions:\ AI Points are issued once per year after successful billing and remain valid for 1 year.\ Example: * If you receive 1000 AI Points on January 1, 2025, they will expire on January 1, 2026. * On the same date, a new annual allocation of 1000 AI Points will be issued. \ Purchased AI Points (Point Packs):\ Point Packs are additional AI Points purchased by users with an active subscription. Purchased AI Points are valid for 1 year from the purchase date.\ \ Subscription Status Requirement:\ AI Points can only be used during an active subscription period.\ If your subscription expires, unused points will remain in your account but cannot be used until the subscription is reactivated. Before each project is processed, we calculate and display the number of AI Points it will consume so you can review the cost in advance. To view your past point usage, click your profile avatar in the top-right corner and select **Points Usage History**. There, you can see a detailed record of all historical AI Points consumption. Vozo is primarily subscription-based and does not currently offer a pure pay-as-you-go model. You can select a plan based on your expected usage, or start with the **Creator** plan if you’re unsure. You can upgrade your plan at any time to better match your usage, or purchase additional one-time Points Packs as needed. If your usage is higher and you need a larger quota, you can request a Custom Plan. Please contact our BD team via the chat button in the bottom-right corner, or email us at [**bd@vozo.ai**](mailto:bd@vozo.ai). The **Pro Plan** is no longer available for purchase on the web and is now offered only in the Vozo mobile app, where it includes mobile-specific features. On the web, the Pro Plan supports subtitle translation only and does not include AI Points. Features that consume AI Points, such as AI dubbing or Lip Sync, are not available under this plan. To access AI dubbing, Lip Sync, or other point-based features on the web, please upgrade or subscribe to a higher-tier plan. # Add Pause Source: https://www.vozo.ai/docs/edit_script_dub/add_pause Manually insert pauses to control the pacing of your speech. In the **Speech** section, click the sentence where you want to add a pause. Move your cursor to the exact position in the sentence where you want the pause. Click the **Add Pause** button in the toolbar, then choose the desired pause duration. Click **Generate Speech** to apply the changes and regenerate the audio. Need a longer break? Just insert multiple pause commands in a row.\ For example, adding a 1-second pause twice results in a 2-second break. # Rewrite with AI Pilot Source: https://www.vozo.ai/docs/edit_script_dub/ai_pilot Use AI Pilot in Voice Studio to rewrite, improve, or fully regenerate your script using prompts. ## Edit a Single Sentence 1. Click on the sentence you want to edit to activate the toolbar. Then click **Rewrite with AI**. 2. Enter a custom instruction or select a preset option, such as: > Refine the text to sound more humble.\ > Make the text shorter. 3. AI Pilot will generate an updated version. * If satisfied, click **Apply to Script**. * If not, hover over the command, click **Edit Prompt**, revise your instruction, and resend it. 4. After applying the edits, click **Generate Speech** to regenerate the audio for that segment. ## Rewrite the Whole Script 1. Click **AI Pilot** at the bottom-right corner of the **Speech** section. 2. Enter a custom instruction or select a preset option, such as: > Rewrite the transcript as an advertisement for Vozo.\ > Refine the text in a formal way. 3. AI Pilot will update the entire script. * If satisfied, click **Apply to Script**. * If certain sentences don’t need changes, hover over them and click **Use the Original Script**. * If unhappy with the full result, hover over the command, click **Edit Prompt**, modify your instruction, and resend it. 4. After applying edits, make any final manual adjustments and click **Generate Speech** to regenerate the updated audio. # Change Voice Source: https://www.vozo.ai/docs/edit_script_dub/change_voice Switch to a different voice for any segment in your script. Click the **voice tag** on the left side of the sentence to open the **Voice Library**. Choose from one of the following voice sources: * **In This Project**: Voices that are already used or have been detected in this project. * **AI Voice**: A wide selection of ready-made AI voices. * **Cloned Voice**: Your previously saved custom cloned voices, or upload audio now to clone a new voice instantly. Click **Confirm** to apply the selected voice. To replace all segments using the current voice, check **Apply changes to all speeches of xxx** before confirming. Segments with modified voices will be highlighted. Click **Generate Speech** to regenerate the audio with the new voice. Speech generation consumes points. For details on point calculation, see [Points Usage for Speech Generation](/docs/common/speech-points-rules). # Edit Speech Source: https://www.vozo.ai/docs/edit_script_dub/edit_speech Use Voice Studio to modify your script and regenerate speech with the same voice and tone. Click on the sentence you want to edit to activate editing. Make your changes to the text. Click the **Generate Speech** button to regenerate the audio for that segment. If you have multiple sentences to adjust, complete all edits first, then click the **Generate Speech** button at the top of the Speech section to batch-generate audio for all modified segments. Speech generation consumes points. For details on point calculation, see [Points Usage for Speech Generation](/docs/common/speech-points-rules). # Get Started Source: https://www.vozo.ai/docs/edit_script_dub/get_started Learn how to create or edit speech using Voice Studio — whether starting from scratch or editing with existing audio/video. ## Start a Project You can begin in two ways: * **Create New Project**: Start from a blank project and generate speech from text. * **Import Audio/Video**: Upload existing media to edit the speech, change voice, or add new voice-over. ## Configure Your Project If you choose **Import Audio/Video**, you'll need to configure the following before processing begins: * **Language Spoken**: Select the language spoken in your uploaded audio or video, or choose **Auto-Detect** to let the system identify it automatically. * **Number of Speakers**: Choose the number of speakers or use **Auto-Detect** for automatic speaker separation. Providing the correct number improves accuracy. Click **Continue** to proceed. If you selected **Create New Project**, you can skip this step and begin generating speech directly from your script. ## Edit Speech ### Generate Speech * In the Speech section, click **Add Segment**. * Enter your text, choose a voice (from the left side of the text), and click the **Generate Speech** button. Voice Studio Generate Gi ### [Edit Speech](/docs/edit_script_dub/edit_speech) * Click on the sentence you want to edit. * After editing, click **Generate Speech** to generate audio for that sentence. ### [Rewrite with AI Pilot](/docs/edit_script_dub/ai_pilot) * Click a sentence and choose **Rewrite with AI** in the toolbar. * Provide a prompt and preview the result. * To rewrite the entire script, use the **AI Pilot** button at the bottom right of the Speech section. ## Adjust Audio Timing and Speed Use the timeline at the bottom to fine-tune audio playback. ### Adjust Timing Drag the speech audio block left or right to shift its position. Adjust speech timing ### Adjust Speed Hover over either edge of a speech block to reveal a handle. Drag to stretch or compress for speed control. Adjust speech speed ## Lip Sync After generating speech, you can sync lip movements with the new audio. Lip Sync is only available for projects with uploaded **video**. 1. Click the **Lip Sync** tab on the left. 2. Refer to [Get Started with Lip Sync](/docs/lipsync/get_started) for configuration. 3. Start lip sync to automatically match mouth movement with the updated voice. ## Export and Download Once you're satisfied with your edits: * Click **Export** at the top-right corner. * After rendering is complete, click **Download** to get your final audio or video. ## FAQ Please refer to the [Points Usage for AI Tools](/docs/common/tools-points-rules) for detailed pricing rules. # Speed, Volume, Pitch Source: https://www.vozo.ai/docs/edit_script_dub/speed_volume_pitch Adjust the speed, volume, and pitch of generated speech in the timeline. Click on the speech audio clip you want to adjust in the timeline. Click the **Speed / Volume / Pitch** icon in the top-left corner of the timeline to open the control panel. Modify the speed, volume, or pitch values as needed. Use the preview to hear the changes before applying. To apply the same settings to all speeches by the same voice, check **Apply change to all speeches of xxx**. Click anywhere outside the control panel to apply the adjustments. You can also adjust speed by stretching or shrinking the audio clip directly on the timeline. # Face Swap Source: https://www.vozo.ai/docs/face_swap/get_started Use Face Swap to replace the face in a video with a target face photo. ## Overview **Face Swap** allows you to replace a person’s face in a video with a different face photo. This feature currently supports **videos only** and is available under **Lab** features. ## How to Use On the **dashboard**, click **Dashboard - Labs**, then select the **Face Swap** tool. Upload your **original video** and the **target face photo** you want to use for replacement. For videos with multiple faces, all detected faces will be replaced.\ To ensure best results, please upload videos that contain only **one face**. Click the **Face Swap** button to begin processing.\ During peak server hours, you may need to wait in a queue before processing starts. ## Access & Limits Free users can try Face Swap **up to 2 times**. To continue using this feature, upgrade to a paid membership. ## FAQ Please refer to the [Points Usage for AI Tools](/docs/common/tools-points-rules) page for detailed pricing rules. # Product Overview Source: https://www.vozo.ai/docs/index Vozo lets you easily generate, edit, and translate videos — all in one place. This Help Center offers step-by-step guides to help you get started quickly. ## What do you want to do? Find step-by-step guides to help you start using each tool or answer common questions. Translate and dub using AI-cloned voice. Add translated or bilingual subtitles. Detect and translate on-screen text in videos. Sync lips in your video with any audio. Turn your photo into a lifelike talking video. Text-based voice editing, cloning and TTS. Repurpose long videos into viral shorts. Includes experimental tools like Face Swap. ## Other things you might be looking for Learn which languages are supported in AI translation and speech generation. Learn how to subscribe, upgrade, cancel, manage billing, and access invoices. Learn how points are consumed when using different AI tools in Vozo. Learn how to invite teammates, share projects, and manage member roles and permissions. If you’re looking for something else, use the left navigation, the search bar at the top, or the Ask a Question box at the bottom to find what you need. ## Frequently Asked Questions Subscribe to any Vozo plan and watermarks will be automatically removed from your projects. You will need to re-export or re-download your project video for the watermark to be removed in the final file. On your Project page, click the **Export** button in the top-right corner. If the video needs to be exported first, please wait for 1–2 minutes.
Once the export is complete, a **Download** button will appear. Click the button to download the video to your device. New users receive free points upon registration, valid for 7 days. To continue using Vozo, subscribe to a plan to get more points. If you didn’t receive any free points after signing up, it may mean that you have previously registered with another account, or your account has been flagged for fraudulent activity. Different tools have different point consumption rules. Please visit our [Pricing page](https://app.vozo.ai/pricing) and click [**View Full Rules**](/docs/common/tools-points-rules) for details. To ensure sustainable and efficient use of our cloud resources: * For **free users**, projects will be cleared **30 days after registration**. * For **paid users**, projects are retained throughout your subscription. After your membership expires, they will be cleared **90 days later**. Please make sure to download your generated video or audio results before that time. Click the **Support** button in the bottom-right corner of any page to message our support team, or email us at [**support@vozo.ai**](mailto:support@vozo.ai) requesting account deletion. Once deleted, your account cannot be restored, and you will not receive free points again if you re-register. # Lip Sync Editor Source: https://www.vozo.ai/docs/lipsync/edit_lipsync Use the Lip Sync editor to mark the correct speaker and achieve perfect lip sync. Vozo automatically analyzes your video and applies lip sync to the **detected speaking face**, which is especially useful for multi-person scenes. After processing, you can edit speaker markings in the editor to specify which face should or shouldn’t be synced during specific time segments. ## Show Original Video & Mark Speaker Toggle the **Check & Edit Lip Sync** switch at the bottom-left corner of the editor to view a side-by-side comparison: Lip Sync Edit Lip Sync * Left: the **original video** * Right: the **generated video** In the original video preview, all detected faces will be labeled: * **Marked Speaker** — this face is identified as the current speaker and has been synced to the audio. * **Not Speaker** — this face is not identified as the speaker and remains in its original state without lip sync. ## How to Mark the Speaker * If the speaking face was not correctly recognized as the speaker, click **Mark as Speaker** button. * If no one in the frame is actually speaking (for example, during a voiceover or narration), click **Not Speaker** on the incorrectly marked face. Click **Regenerate x Edited Clips** to update all segments with modified markings. ### Mark Specific Time Segments Vozo automatically splits your video into multiple timeline clips.\ If the part you want to edit isn’t already separated, you can split it manually: Drag the playhead to the time point you want to isolate. Click the **Split** button in the top-left corner of the timeline to create a new clip. Lipsyncsplit Pn Adjust the speaker marking for the new segment as needed. ## Common Scenarios and Solutions When multiple faces appear in a scene, Vozo might apply lip sync to the wrong one. **How to fix:** 1. In the original video preview, click the correct face and choose **Mark as Speaker**.  The incorrect face will automatically be unmarked. 2. Click **Regenerate x Edited Clips** to update the result. If the audio comes from an off-screen narrator or background voice, the system may still apply lip sync to a visible face. **How to fix:** 1. Select the synced face and click **Not Speaker**. 2. Click **Regenerate x Edited Clips** to remove lip sync and restore the original mouth motion. Sometimes, lip sync can make the mouth appear over objects like microphones or hands. **How to fix:** 1. Click **Split** to isolate that segment on the timeline. 2. Select the segment and click **Not Speaker**. 3. Click **Regenerate x Edited Clips** to remove lip sync. This fix is best for short, temporary obstructions.\ If the face is frequently covered, it may not be suitable for lip syncing. Lip sync may generate unwanted mouth movement when the speaker is silent. **How to fix:** 1. Click **Split** to isolate the part where the issue occurs. 2. Click **Not Speaker** for the face in that segment. 3. Click **Regenerate x Edited Clips** to apply the update. During fade-in or fade-out transitions, lip sync may create distorted facial effects. **How to fix:** 1. Click **Split** to separate the transition from the rest of the video. 2. Click **Not Speaker** for the face in that segment. 3. Click **Regenerate x Edited Clips** to finalize. Removing sync during transitions helps maintain a more natural look between scenes. # Get Started Source: https://www.vozo.ai/docs/lipsync/get_started Lip Sync allows you to sync the lip movements of people in the video with the new audio, supporting both single and multiple speakers. ## Create a Project ### Upload Video To get started, navigate to your **Dashboard** and click **Talking Video Generator - Start with Video**. This will open the upload dialog, where you can drag and drop your video files or click to upload. You can also paste a link to upload your video. In addition, you can also create a project from the **Translate & Dub** or **Voice Studio** projects by clicking the **Lip Sync Tab** on the left side. This will allow you to use the new dubbing to drive the lip sync. ### Input Audio There are several ways to create or provide audio for Lip Sync: #### 1. Text-to-Speech You can generate audio by entering text directly. To create the voice for Lip Sync, you can: * Clone a voice directly from the current video * Select an existing voice from the **Voice Library** * Choose **Choose from Library → Clone Voice → Clone New Voice** to create a new cloned voice and use it for speech generation The generated speech will then be used to drive the lip sync. #### 2. Upload an Audio File You can upload a pre-recorded audio file, and the system will use this audio to generate the lip-synced video. #### 3. From This Video If your video already contains the newly created audio as its soundtrack, select this option. The system will directly use the video's current audio track to drive the lip sync and synchronize the speaker’s mouth movements accordingly. ### Number of Faces in the Video If only one face appears throughout the video, select “Only 1 Face”. If multiple faces appear (including non-speaking or animated faces), select “Auto-Detect”. The system will automatically identify who is speaking in each shot and apply lip sync accordingly. ## Edit the Lip Sync Face Once the video is generated, you can preview the lip-synced result. If you find that Lip Sync has been applied to the wrong face or to a segment where it shouldn't have been synced, you can easily make edits in the [Lip Sync editor](/docs/lipsync/edit_lipsync). ## Download the Video If you are satisfied with the video, click the **Download/Export** button in the top-right corner to download the lip-synced video. ## FAQ * **Resolution**: Same as the original uploaded video * **Frame rate**: Fixed at **25fps** * **Encoding**: **H.264** * **Bitrate**: Dynamically adjusted to maintain quality; may differ from original Please refer to the [Points Usage for AI Tools](/docs/common/tools-points-rules#lip-sync) for detailed pricing rules. # Create Variant with New Audio Source: https://www.vozo.ai/docs/lipsync/variants Learn how to create a new Lip Sync variant by uploading a different audio within the same project. This feature is available to **Studio** and higher-tier members. ## What Is a Variant A **variant** is a new output generated from the same Lip Sync project using a different audio.\ It allows you to produce multiple versions while keeping the same trained model. ## Why Create a Variant Instead of a New Project Creating a variant reuses the model that was already trained in your project.\ Compared with starting a new project: * ⚡ **Much faster** — usually completes within minutes instead of tens of minutes or hours. * 🎯 **More consistent** — keeps the same lip-sync accuracy and visual quality.   * 💰 **Cost-saving** — only 5 points per minute are charged, with **no additional 5 base points**. ## How to Create a Variant Go to your Lip Sync project and click **Create with New Audio** in the top-right corner. Upload a new audio file, or enter text to generate speech via Text to Speech. Click **Generate** and wait for the process to complete. All variants are stored under the same project.\ Click the Variant option in the top-right corner to open the dropdown and switch between variants, preview, or download. # Edit Shorts Source: https://www.vozo.ai/docs/shorts/edit_shorts Learn how to trim, edit captions, pick templates, and adjust styles when editing your generated Shorts. On the Shorts List page, select the short video you want to edit and click the **Edit** button on the right to enter the Shorts editor. Shorts Editor Pn ## Trim & Extend Click on the **Trim & Extend** tab in the sidebar to edit the clip's intro and video range. ### AI Intro * **Enable AI Intro**: If enabled, an AI-generated intro will appear in the first 3 seconds of the video. * **Regenerate or Edit Intro**: If you're not satisfied with the generated intro, click the **Regenerate** button to let AI generate a new one, or manually edit the text. * **Disable Intro**: If you don't need an intro, toggle off the switch. ### Trim Video In this section, you’ll see the **transcript of the original video**. The highlighted parts correspond to the clip's included segments. * **To Trim a Segment**: Select the text corresponding to the part you want to remove, then click the **Trim** button. * **To Extend a Segment**: Select the crossed-out text you want to include and click the **Extend** button. The selected segments can be non-contiguous. For example, if there is an unnecessary sentence in the middle that you want to remove, you can trim it while keeping the content before and after intact. ## Correct Captions The captions are automatically generated by AI. If you notice any errors, click the **Correct Captions** tab on the left sidebar. From there, you can edit and correct the caption text. ## Pick a Template Vozo offers several preset templates for you to choose from. A template includes the following elements: * **Caption Style and Position** * **Intro Style and Position** * **Reframing Layout** * **Logo Image and Position** ### Create New Template If you’ve customized styles in the **Edit Style** section, you can save them as a template by clicking **Create New Template**. This allows you to reuse the same style for other videos. ## Edit Style In this section, you can customize various style elements, including: ### Captions Choose a preset style or customize options like font, color, and animations. ### Intro Enable this to display an intro for the first 3 seconds (captions won't appear during this time). Currently, intro styles can only be selected from presets. ### Branding #### Reframing Layout * **Auto**: Automatically centers the main subject of the original video in the vertical frame. * **Fit**: Fits the entire original frame into the layout. #### Logo Upload your logo, watermark, or overlay to place it on the video. ## Adjust Framing Framing behavior depends on the **Reframing Layout** setting. * If **Fit** is applied, you can adjust the position of the fit frame here, and the change will apply to the entire video. * If **Auto** is applied, Vozo divides the video into segments based on scene changes. You can adjust the layout and framing for each segment individually. Simply play the video, and when it reaches the next segment, make your adjustments. ## Export and Download After completing all edits, click the **Export** button in the top-right corner. Once the export process finishes, you can download the video. # Get Started Source: https://www.vozo.ai/docs/shorts/get_started Learn how to use Long Video to Shorts to automatically extract highlight moments and generate multiple viral short videos. ## Upload Your Video You can upload your video in two ways: * Paste a video link. * Upload a video file. Only English talking videos are supported. ## Configure Your Project ### Preferred Shorts Length Select your desired lengths for the short videos. You can choose multiple options or select **Auto** to let the system decide. ### Pick a Template Choose your preferred subtitle style for the shorts. ### Select Time Range (Optional) Enable this option if you want to limit highlight extraction to a specific part of the video. This can save points, as usage is based on the original video’s duration. Once configured, click **Start Clipping** to begin. ## Preview and Export Shorts Once generation is complete, you'll receive multiple Shorts along with **Virality Score** and **Insights**. * **Preview**: Watch each short and review its transcript and virality metrics. * **Mark as Favorite**: Click the star icon to save the ones you like. Shorts Pn ## Download Shorts 1. Click the **Export** button on a short. 2. The short will appear in the export queue. 3. Once ready, click to download the video. ## Advanced Features ### Edit Shorts Click **Edit** to modify clip range, subtitle text, or style. Shorts Edit Button Pn ### Translate Shorts Click **Translate** to convert the video into another language and dub it using the original voice. ## FAQ Please refer to the [Points Usage for AI Tools](/docs/common/tools-points-rules) page for detailed pricing rules. # Subscriptions & Billing Source: https://www.vozo.ai/docs/subscription Learn how to subscribe, upgrade, cancel, manage billing, and access invoices. ## Start Your Subscription To subscribe to Vozo or compare available plans, visit our [Pricing page](https://app.vozo.ai/pricing). You can view the features, point allocations, and pricing for each plan there. ## Cancel Your Subscription If you no longer need our services, you can easily cancel your subscription at any time. 1. Go to [Subscription Settings](https://app.vozo.ai/subscription). 2. Click **Manage Subscription** and select **Cancel Subscription**. 3. Your current plan and points will remain available until the end of the current billing cycle. No cancellation fees will apply, and no further payments will be made after that. 4. To resume your subscription later, simply click **Renew Subscription**. During your subscription period, all your projects will remain stored in the cloud.   To ensure sustainable and efficient use of our cloud resources, your projects will be **automatically deleted 90 days after your subscription expires**. Please make sure to download any generated videos or audio results before that time. If your project data is important to you, we recommend you **downgrade to a lower-tier plan** to retain cloud storage access. ## Upgrade or Downgrade Your Plan If you’re already subscribed and need more points or access to advanced features, consider upgrading your plan. If your needs have decreased, you can downgrade to reduce costs: 1. Go to the [Pricing page](https://app.vozo.ai/pricing). 2. Choose the plan that suits your needs. ### When you upgrade to a higher plan * The upgrade takes effect immediately. You are charged the full price of the new plan right away, your account is switched to the new plan, and you receive a full new allocation of AI Points immediately. * Any unused AI Points from your previous plan remain available until their original expiration date and will not be forfeited due to the upgrade. * Example: If your Monthly plan started on January 1 and you upgrade to a higher plan on January 15, you will be charged for the new plan on January 15 and receive the full AI Points allocation of the new plan immediately. Any remaining AI Points from your previous Monthly plan will remain usable until their original expiration date. ### When you downgrade to a lower plan * The downgrade takes effect at the end of your current billing cycle. Until then, you can continue using your current plan and all its benefits. * The lower plan price will be charged starting from the next billing cycle. * Example: If you downgrade on January 15 and your current billing cycle ends on January 31, your existing plan will remain active through January 31. On February 1, you will be charged for the lower plan, your account will switch to the new plan, and you will receive the AI Points allocation for that plan. ## How to Get More AI Points If you want to keep your current plan but need additional points temporarily, you can purchase a Points Pack. Points Packs provide a one-time top-up of AI Points without changing your subscription plan or billing cycle. This option is available to users with an active subscription. Free users need to subscribe first before purchasing a Points Pack. 1. Go to the [Pricing page](https://app.vozo.ai/pricing). 2. Scroll down below the plan cards to find the Points Pack purchase section. 3. Select the number of points you want to purchase. After payment, the points will be added to your account immediately. ## View Payment and Billing History 1. Go to [Subscription Settings](https://app.vozo.ai/subscription). 2. Click **Manage Subscription** and select **Billing & Payments**. 3. You’ll see a history of your past subscriptions, payments, and invoices. ## Get Your Invoice or Receipt 1. Go to [Subscription Settings](https://app.vozo.ai/subscription). 2. Click **Manage Subscription** and select **Billing & Payments**. 3. Ensure your billing information is correct if you plan to download a new invoice or receipt. (Changes only apply to documents not yet downloaded.) 4. In the **Invoice History** section, locate the relevant order. 5. Click to **Download Invoice** or **Download Receipt**. ## FAQ New users receive gift AI points upon registration, valid for 7 days. To continue using Vozo, subscribe to a plan to get more points. If you didn’t receive any free points after signing up, it may mean that you have previously registered with another account, or your account has been flagged for fraudulent activity. AI Points follow different validity rules depending on how they are issued. Please refer to the details below.\ \ Gift AI Points (for new users):\ Gift AI Points are valid for 7 days from the date of account registration. Any unused Gift AI Points will be automatically cleared after 7 days.\ \ Monthly Subscriptions:\ AI Points are issued each month after successful billing.\ Each monthly allocation is valid for 2 months, meaning that unused AI Points are automatically carried over to the next month.\ Example: * 100 AI Points issued on January 1 will expire on March 1. * You’ll also receive 100 AI Points for February on February 1, which will expire on April 1. \ Annual Subscriptions:\ AI Points are issued once per year after successful billing and remain valid for 1 year.\ Example: * If you receive 1000 AI Points on January 1, 2025, they will expire on January 1, 2026. * On the same date, a new annual allocation of 1000 AI Points will be issued. \ Purchased AI Points (Point Packs):\ Point Packs are additional AI Points purchased by users with an active subscription. Purchased AI Points are valid for 1 year from the purchase date.\ \ Subscription Status Requirement:\ AI Points can only be used during an active subscription period.\ If your subscription expires, unused points will remain in your account but cannot be used until the subscription is reactivated. If a project fails to process due to technical issues, the points deducted will be automatically refunded. For subscription payments, we currently do not offer refunds. To help you make an informed decision, we offer gift points to new users for a free trial of our features. Please take advantage of this opportunity to experience our services before subscribing to avoid any impulsive purchases. If you have already subscribed but decide not to continue using our services, please cancel your subscription before the next billing cycle to avoid further charges. If you need a refund due to unauthorized credit card transactions, please contact our support team. We accept a range of payment methods, including **credit and debit cards** (Visa, Mastercard, American Express, Discover, Diners Club, JCB, and China UnionPay) as well as **Apple Pay**, **Cash App Pay**, **Google Pay**, **Alipay**, and **Link**. All transactions are securely processed through **Stripe**, a trusted payment platform. Vozo is primarily subscription-based and does not currently offer a pure pay-as-you-go model. You can select a plan based on your expected usage, or start with the **Creator** plan if you’re unsure. You can upgrade your plan at any time to better match your usage, or purchase additional one-time Points Packs as needed. If your usage is higher and you need a larger quota, you can request a Custom Plan. Please contact our BD team via the chat button in the bottom-right corner, or email us at [**bd@vozo.ai**](mailto:bd@vozo.ai). If you need to generate a large number of videos, please contact our BD team for a customized pricing plan.\ When reaching out, please share the features you need and your estimated monthly usage. You can contact us by clicking the chat button in the bottom-right corner of the product page or emailing [**bd@vozo.ai**](mailto:bd@vozo.ai). The **Pro Plan** is no longer available for purchase on the web and is now offered only in the Vozo mobile app, where it includes mobile-specific features. On the web, the Pro Plan supports subtitle translation only and does not include AI Points. Features that consume AI Points, such as AI dubbing or Lip Sync, are not available under this plan. To access AI dubbing, Lip Sync, or other point-based features on the web, please upgrade or subscribe to a higher-tier plan. Possible reasons include: * Your cancellation wasn’t fully completed (the final confirmation step was not finished), so the subscription remained active. * You chose to **pause** the subscription (e.g., for 1–2 months); after the pause period ended, the subscription automatically resumed. * Another account you own may have an active subscription. If any of the above applies, please contact support — click the chat button at the bottom-right of the product page or email [**support@vozo.ai**](mailto:support@vozo.ai). Our team will help verify and resolve the issue. # Supported Languages Source: https://www.vozo.ai/docs/supported_languages Learn which languages are supported in AI translation and speech generation. Vozo supports translation and speech generation for most major languages worldwide. Expand the sections below to view the supported languages for each feature, or click Ask AI on this page for quick assistance. *** ## Translate & Dub / Translate Subtitles Albanian (Albania) Arabic (Egypt, Morocco, Saudi Arabia, Syria, United Arab Emirates) Azerbaijani (Azerbaijan) Basque (Spain) Bengali (India) Bosnian (Bosnia and Herzegovina) Bulgarian (Bulgaria) Cantonese (China) Catalan (Spain) Chinese (China, Hong Kong, Taiwan) Croatian (Croatia) Czech (Czech Republic) Danish (Denmark) Dutch (Belgium) English (Australia, Canada, Ghana, Hong Kong, India, Ireland, Kenya, New Zealand, Nigeria, Philippines, Singapore, South Africa, Tanzania, United Kingdom, United States) Filipino (Philippines) Finnish (Finland) French (Belgium, Canada, France, Switzerland) Galician (Spain) German (Austria, Germany, Switzerland) Greek (Greece) Gujarati (India) Hebrew (Israel) Hindi (India) Hungarian (Hungary) Icelandic (Iceland) Indonesian (Indonesia) Italian (Italy, Switzerland) Japanese (Japan) Kannada (India) Kazakh (Kazakhstan) Korean (South Korea) Latvian (Latvia) Lithuanian (Lithuania) Macedonian (North Macedonia) Malay (Malaysia) Malayalam (India) Maltese (Malta) Marathi (India) Mongolian (Mongolia) Nepali (Nepal) Norwegian (Norway) Persian (Iran) Polish (Poland) Portuguese (Brazil, Portugal) Punjabi (India) Romanian (Romania) Russian (Russia) Serbian (Serbia) Slovak (Slovakia) Slovenian (Slovenia) Somali (Somalia) Spanish (Argentina, Bolivia, Chile, Colombia, Costa Rica, Cuba, Dominican Republic, Ecuador, El Salvador, Equatorial Guinea, Guatemala, Honduras, Mexico, Nicaragua, Panama, Paraguay, Peru, Puerto Rico, Spain, United States, Uruguay, Venezuela) Swahili (Kenya, Tanzania) Swedish (Sweden) Tamil (India) Thai (Thailand) Turkish (Turkey) Ukrainian (Ukraine) Urdu (Pakistan) Uzbek (Uzbekistan) Vietnamese (Vietnam) Afrikaans Albanian Amharic Arabic (Algeria, Bahrain, Egypt, Iraq, Jordan, Kuwait, Lebanon, Libya, Morocco, Oman, Qatar, Saudi Arabia, Syria, Tunisia, United Arab Emirates, Yemen) Armenian Assamese Azerbaijani Bangla Basque Bengali Bosnian Bulgarian Burmese Catalan Chinese (Guangxi – Simplified, Hong Kong – Traditional, Jilu – Simplified, Mainland China – Simplified, Northeastern – Simplified, Southwestern – Simplified, Taiwan – Traditional, Wu – Simplified, Henan – Simplified, Shaanxi – Simplified) Croatian Czech Danish Dutch (Belgium, Netherlands) English (Australia, Canada, Hong Kong, India, Ireland, Kenya, New Zealand, Nigeria, Philippines, Singapore, South Africa, Tanzania, United Kingdom, United States) Estonian Filipino Finnish French (Belgium, Canada, France, Switzerland) Galician Georgian German (Austria, Germany, Switzerland – Standard, Switzerland – Swiss German) Greek Gujarati Hebrew Hindi Hungarian Icelandic Indonesian Inuktitut (Latin, Syllabics) Irish Italian Japanese Javanese Kannada Kazakh Khmer Korean Lao Latvian Lithuanian Macedonian Malay Malayalam Maltese Marathi Mongolian Nepali Norwegian Bokmål Odia Pashto Persian Polish Portuguese (Brazil, Portugal) Punjabi Romanian Russian Serbian Sinhala Slovak Slovenian Somali Spanish (Argentina, Bolivia, Chile, Colombia, Costa Rica, Cuba, Dominican Republic, Ecuador, El Salvador, Equatorial Guinea, Guatemala, Honduras, Mexico, Nicaragua, Panama, Paraguay, Peru, Puerto Rico, Spain, United States, Uruguay, Venezuela) Sundanese Swahili (Kenya, Tanzania) Tamil (India, Malaysia, Singapore, Sri Lanka) Telugu Thai Turkish Ukrainian Urdu (India, Pakistan) Uzbek Vietnamese Welsh Zulu ## Visual Translate Albanian Azerbaijani Basque Bosnian Catalan Chinese (Simplified) Chinese (Traditional) Croatian Czech Danish Dutch English Estonian Finnish French Galician German Hindi Hungarian Icelandic Indonesian Irish Italian Japanese Korean Latvian Lithuanian Malay Maltese Norwegian Persian Polish Portuguese Romanian Russian Serbian Slovak Slovenian Spanish Swahili Swedish Filipino Turkish Uzbek Vietnamese Afrikaans Albanian Amharic Arabic (Algeria, Bahrain, Egypt, Iraq, Jordan, Kuwait, Lebanon, Libya, Morocco, Oman, Qatar, Saudi Arabia, Syria, Tunisia, United Arab Emirates, Yemen) Armenian Assamese Azerbaijani Bangla Basque Bengali Bosnian Bulgarian Burmese Catalan Chinese (Guangxi – Simplified, Hong Kong – Traditional, Jilu – Simplified, Mainland China – Simplified, Northeastern – Simplified, Southwestern – Simplified, Taiwan – Traditional, Wu – Simplified, Henan – Simplified, Shaanxi – Simplified) Croatian Czech Danish Dutch (Belgium, Netherlands) English (Australia, Canada, Hong Kong, India, Ireland, Kenya, New Zealand, Nigeria, Philippines, Singapore, South Africa, Tanzania, United Kingdom, United States) Estonian Filipino Finnish French (Belgium, Canada, France, Switzerland) Galician Georgian German (Austria, Germany, Switzerland – Standard, Switzerland – Swiss German) Greek Gujarati Hebrew Hindi Hungarian Icelandic Indonesian Inuktitut (Latin, Syllabics) Irish Italian Japanese Javanese Kannada Kazakh Khmer Korean Lao Latvian Lithuanian Macedonian Malay Malayalam Maltese Marathi Mongolian Nepali Norwegian Bokmål Odia Pashto Persian Polish Portuguese (Brazil, Portugal) Punjabi Romanian Russian Serbian Sinhala Slovak Slovenian Somali Spanish (Argentina, Bolivia, Chile, Colombia, Costa Rica, Cuba, Dominican Republic, Ecuador, El Salvador, Equatorial Guinea, Guatemala, Honduras, Mexico, Nicaragua, Panama, Paraguay, Peru, Puerto Rico, Spain, United States, Uruguay, Venezuela) Sundanese Swahili (Kenya, Tanzania) Tamil (India, Malaysia, Singapore, Sri Lanka) Telugu Thai Turkish Ukrainian Urdu (India, Pakistan) Uzbek Vietnamese Welsh Zulu ## Lip Sync / Talking Photo Afrikaans Albanian Amharic Arabic Armenian Assamese Azerbaijani Basque Bengali Bosnian Bulgarian Burmese Catalan Chinese Croatian Czech Danish Dutch English Estonian Filipino Finnish French Galician Georgian German Greek Gujarati Hebrew Hindi Hungarian Icelandic Indonesian Inuktitut Irish Italian Japanese Javanese Kannada Kazakh Khmer Korean Lao Latvian Lithuanian Macedonian Malay Malayalam Maltese Marathi Mongolian Nepali Norwegian Bokmål Odia Pashto Persian Polish Portuguese Punjabi Romanian Russian Serbian Sinhala Slovak Slovenian Somali Spanish Sundanese Swahili Swedish Tamil Telugu Thai Turkish Ukrainian Urdu Uzbek Vietnamese Welsh Zulu ## Voice Studio English Chinese Spanish Arabic Russian Portuguese French German Korean Japanese Hindi Turkish Filipino Finnish Czech Danish Dutch Polish Romanian Slovak Swedish Croatian Indonesian Italian Bulgarian Greek Malay Tamil Ukrainian # Get Started Source: https://www.vozo.ai/docs/talking_photo/get_started Learn how to turn a portrait into a talking video using your photo and audio input. ## Create a Project To get started, navigate to your **Dashboard** and click **Talking Video Generator - Start with Photo**. This will open the upload dialog, where you can drag and drop your image files or click to upload. You can input audio in multiple ways: ### Text to Speech If you have a script and want to generate speech from text, select this option. Select your desired language and voice from the dropdown. If you're not satisfied with the voices listed, click *"Choose More from Library"* to explore more options. **Use a Cloned Voice:** Click *"Choose More from Library > Cloned Voice > Clone New Voice"* and follow the instructions to upload or record audio to create your custom voice. Enter your script and click the play button to preview. ### Upload Audio If you already have an audio file, select this option to upload it directly. ## Preview and Download After the video is generated, preview the results directly on the project page. To download the video, click the **Download/Export** button in the top-right corner. ## FAQ * **Resolution**: Exported as **720p**. The system automatically selects the most suitable aspect ratio based on the input image and outputs at a fixed resolution. Possible resolutions include: * **16:9** → 1248×704 * **4:3** → 1120×832 * **1:1** → 960×960 * **3:4** → 832×1120 * **9:16** → 704×1248 * **21:9** → 1504×640 * **Frame rate**: Fixed at **25fps** * **Encoding**: **H.264** * **Bitrate**: Typically around **1100 kb/s**, dynamically varies between **1000–2000 kb/s** depending on content Please refer to the [Points Usage for AI Tools](/docs/common/tools-points-rules#talking-photo) page for detailed pricing rules. # Create Variant with New Audio Source: https://www.vozo.ai/docs/talking_photo/variants Learn how to create a new Talking Photo variant by uploading a different audio within the same project. This feature is available to **Studio** and higher-tier members. ## What Is a Variant A **variant** is a new output generated from the same Talking Photo project using a different audio.\ It allows you to produce multiple versions while keeping the same trained model. ## Why Create a Variant Instead of a New Project Creating a variant reuses the model that was already trained in your project.\ Compared with starting a new project: * ⚡ **Much faster** — usually completes within minutes instead of tens of minutes or hours. * 🎯 **More consistent** — keeps the same facial expressions and movements for a stable visual quality.   * 💰 **Cost-saving** — only 5 points per minute are charged, with **no additional 5 base points**. ## How to Create a Variant Go to your Talking Photo project and click **Create with New Audio** in the top-right corner. Upload a new audio file, or enter text to generate speech via Text to Speech. Click **Generate** and wait for the process to complete. All variants are stored under the same project.\ Click the Variant option in the top-right corner to open the dropdown and switch between variants, preview, or download. # Team Workspace Source: https://www.vozo.ai/docs/team Create a team in Vozo, assign roles, and collaborate on projects with shared access. If you want to organize your work with colleagues or have an external team or expert assist with reviewing and editing your projects, you can create a team and share your projects with them. ## How to Create a Team Creating a team is a feature available to Studio and higher-tier members. On the **dashboard** page, click your **avatar icon**, then select **Create Team** from the dropdown menu. ### 1. Name Your Team Give your team a name, such as your company name or project name.\ You can change the name later. ### 2. Invite Team Members Currently, Vozo only supports inviting members via **email addresses that have not yet registered with Vozo**.\ You can skip this step and invite members later. If the member's email has already been registered with Vozo and cannot be invited, please contact our support team at [support@vozo.ai](mailto:support@vozo.ai). We can help manually delete that account so you can invite them again. ### 3. Complete Setup Once the team is created, your workspace will automatically change to a team workspace.\ All projects and points will now be shared with your team. ## Roles and Permissions ### Team Roles 1. **Admin**: The team creator's role is Admin. Admin has full permissions. (Currently, it is not possible to assign other users as Admin.) 2. **Editor**: Editors can use the Admin's points to create projects, and they have access to and can edit all projects within the team. 3. **Reviewer**: Reviewers cannot create projects (and cannot use the Admin's points), but they can access and edit limited shared projects within the team. ### Role Permissions Comparison | Permission | Admin | Editor | Reviewer | | --------------------------------------- | :---: | :----: | :-----------------------------------------------------------------------------: | | Create Projects | ✅ | ✅ | ❌ | | Share Projects to Reviewer | ✅ | ✅ | ❌ | | Access Translate & Dub Projects | ✅ | ✅ | Access limited shared projects, cannot translate into more languages. | | Access Edit Script & Dub Projects | ✅ | ✅ | Access limited shared projects, and cannot use Points to redeem dubbing tokens. | | Access Video Lip Sync/Talking Photo | ✅ | ✅ | Access limited shared projects. | | Access Long Video to Shorts Projects | ✅ | ❌ | ❌ | | Purchase a Subscription | ✅ | ❌ | ❌ | | Manage Subscriptions | ✅ | ❌ | ❌ | | Redeem Points through Redeem Code | ✅ | ❌ | ❌ | | Manage Team Members | ✅ | ❌ | ❌ | | Duplicate Translate Projects | ✅ | ✅ | ❌ | | Delete Projects | ✅ | ✅ | ❌ | | Move Projects | ✅ | ✅ | ❌ | | Rename Projects | ✅ | ✅ | ✅ | | Manage Folders (Create, Rename, Delete) | ✅ | ✅ | ❌ | ### Role Assignment Tips * For those who need to manage and be responsible for all projects, we recommend assigning them the **Editor** role. * For those who only need to manage parts of the project (such as collaborators from an agency), we recommend assigning them the **Reviewer** role and sharing specific projects with them. ## Manage Team Members After creating a team, click on your avatar icon and click **Team** from the dropdown menu. From here, you can add or manage members. ### Adding New Members 1. Click the **Add Members** button and enter the email of the person you wish to invite. Currently, Vozo only supports inviting members via **email addresses that have not yet registered with Vozo**. 2. Click the **Invite** button. Vozo will send an invitation email to the provided email address. 3. The invited person must click the **Accept Invitation** button in the email to automatically register with Vozo and join your team. Invitation emails are valid for 24 hours. If the invited person doesn’t accept the invitation within 24 hours, please resend the invite. The invited user must click the Accept Invitation button in the email to register with Vozo and join the team. If they directly register with Vozo, they will create a personal account and will not be able to join the team. ### Managing Team Members On the **Team** page, you can modify members' roles or remove members from the team. ## Share Projects * **Editors** can directly access and edit all projects within the team, so there is no need to share individual projects with them. * **Reviewers** can only access and edit projects shared by Admins or Editors. To share a project with a Reviewer: 1. Go to the project page. 2. Click the **Share** button in the top-right corner. 3. Select the Reviewer and share the project with them. Once shared, the Reviewer will have access. If they haven't accepted the invitation yet, they will gain access once they join the team. Non-team members cannot be given access to projects. Please invite them to join the team first. While sharing is possible within the same team, please avoid multiple people editing the same project simultaneously to prevent data overwrites. ## FAQ Different subscription plans include different default seat allocations. Please refer to our [Pricing](https://www.vozo.ai/pricing) page for the latest details. For Enterprise plans, please contact sales ([bd@vozo.ai](mailto:bd@vozo.ai)) to discuss seat allocation and pricing options. Yes, your points are automatically shared with team members for project creation.\ Members with the **Editor** role can use your points to create projects.\ Members with the **Reviewer** role cannot use your points. Currently, only email addresses that are not registered with Vozo can be invited to join a team.\ If you want to invite an already registered email, please click the **Support** button in the bottom-right corner of any page or email [support@vozo.ai](mailto:support@vozo.ai) for assistance.\ We can help manually delete the existing account so you can invite the email again. Click on your avatar icon on the **dashboard** page, go to **Team**, then open the **Team Profile** tab to edit your team name. No, each account can only create one team. Currently, deleting a team is not supported. However, you can remove all team members to ensure your projects and points are no longer shared. If your Studio/Enterprise subscription expires or you downgrade to a lower-tier subscription, your team access will be suspended.\ You will still be able to create projects and access or edit all projects as usual.\ However, your team members will no longer be able to view or edit team projects, nor use your points to create new projects. # Add Pause Source: https://www.vozo.ai/docs/translate_dub/add_pause Manually add pauses to control the pacing of your translated speech. In the **Speech** section, click the sentence where you want to add a pause. Move your cursor to the exact position in the sentence where you want the pause. Click **Add Pause** from the menu that appears, then choose the desired pause duration. Click **Generate Speech** to apply the changes and regenerate the audio. Need a longer break? Just insert multiple pause commands in a row. For example, adding a 1-second pause twice results in a 2-second break. # Add Subtitles Source: https://www.vozo.ai/docs/translate_dub/add_subtitles This guide will show you how to add subtitles to your translated video. ## Enable Subtitles 1. Click the **Subtitles** tab on the left panel. 2. Toggle the **Add Subtitles** switch. 3. Wait for about 1 minute for the subtitles to be generated. Subtitles will then be embedded into both the original video and the translated video. ## Switch Subtitle Language * **Original**: Adds subtitles in the original language. (Use this if you want to display the original subtitles in your video to provide viewers with accurate access to the original content.) * **Translated (Default)**: Adds subtitles in the translated language, which will align with the new dubbing. ## Customize Subtitle Style You can modify the style of your subtitles: 1. Choose from a selection of preset styles, which include simple and standard subtitle designs as well as more elaborate animated subtitles. 2. Customize the subtitle style manually, such as font, size, and color. Click **Create New Style** to save your customized style for future use. ## Adjust Subtitle Position and Width In the video preview area, you can: * Adjust the position of the subtitles. * Modify the width to suit your video layout. # AI Pilot Source: https://www.vozo.ai/docs/translate_dub/ai_pilot Learn how to use AI Pilot to adjust, refine, and personalize translations for better accuracy and style. ## Overview AI Pilot can assist with handling both the original and translated text. You can: * Quickly correct the original text * Tune translations to better fit your needs * Use back translation to check accuracy * Ask any translation-related questions Currently, AI Pilot cannot modify speaker tags or handle voice/audio timing. ## How to Use ### **Edit a Specific Line** 1. Click the text you want to modify to activate the toolbar. 2. Click **Tune Translation**. 3. Choose a preset or select **Custom Prompt** to enter specific instructions. ### Edit the Entire Translation Aipilotposition Pn 1. Click the **AI Pilot** at the bottom-right of the Speech section. 2. Enter your custom instructions in the dialog box to adjust the entire translation. ## Example Prompts ### Correct Original Text If there are repetitive errors in the recognized original text, such as misidentified brand names or personal names, you can instruct AI Pilot to help you fix them. > **Case 1: Simple Find and Replace** > > *Find Voza and replace it with Vozo in the original script.* > > **Case 2: Advanced Find and Replace** > > *Find all possible misidentified versions of "Josie" in the original text (e.g., Josy, Jessie) and replace them with "Josie".* ### Tune Translation The translation automatically generated for each project is the best interpretation AI has made based on the current context. However, you can still input prompts to adjust the translation, including: modifying the language style, re-translating slang, adjusting the translation length, handling proper nouns specially, and more. > **Case 1: Adjusting Language Style**\ > *​Modify the translation to create a more informal and approachable tone, as if the content were part of a casual dialogue.* > > **Case 2: Re-translating Slang**\ > ​The phrase “Break a leg” means “good luck” in English. Please translate it more naturally. > > **Case 3: Adjusting Translation Length**\ > *​Refine the translation to ensure it takes about the same time to speak as the original text.* > > **Case 4: Special Handling of Proper Nouns**\ > *​Keep all names and place names in their original language without translating them.* ### Check Back Translation If you don't speak the target language, ask AI Pilot to translate the result back into the original language to check for accuracy. > **Case:** > > *Translate the translated text back to English.* ### Any Translation Questions > **Case:** > > Why did you translate “stakeholder” as “parte interesada”? ## Apply or Discard For content modification prompts, the AI Pilot will provide the modified text for each segment and give an explanation for the changes. You can choose whether to apply the suggested modifications. * Click **Apply** to confirm. * Click **Discard** to reject. * Click **Further Refine** to provide more guidance. You can also **hover over each segment** to individually apply or discard changes. Aipilotsegment Pn After clicking **Apply**, the modified text will be applied to the segment. However, the dubbing will not update automatically, and you can still manually edit the translation if needed. Once you're satisfied with the translation, click **Generate Speech** to update the dubbing. # Auto Align Audio & Video Source: https://www.vozo.ai/docs/translate_dub/auto_align_audio_video Automatically align video and audio by adjusting speed segment by segment to fix timing mismatches after dubbing. ## What is Auto Align Audio & Video Auto Align Audio & Video automatically adjusts both video and audio speed segment by segment to keep them aligned. This solves common mismatch issues caused by different speech lengths across languages after dubbing. For example, when translated speech becomes longer or shorter than the original, this feature ensures the video stays synchronized with the new audio. Auto Align Audio&video ## When to Use Use this feature when: * The dubbed audio does not match the original video timing * There are noticeable delays or overlaps between speech and visuals * You want a fully synchronized video without manual adjustment ## How to Apply You can use this feature in two ways: ### 1. Enable after upload After uploading your video, go to **Advanced Settings** and turn on **Auto-Adjust Video Speed for Alignment**. Settings Alignment ### 2. Apply in editor After completing dubbing edits, click **Auto Align Audio & Video** on the timeline to automatically align the video and audio. Processing may take some time. For best results, run alignment after you have finished all dubbing edits. If you are not satisfied with the result, you can undo the alignment using your system undo shortcut (Ctrl + Z or Command + Z). Make sure to stay on the current editor page — do not refresh or leave, otherwise the undo will no longer be available. Editor Alignment ## What Happens After Alignment Video and audio are sped up or slowed down segment by segment to ensure perfect alignment between visuals and audio. The overall duration of the video and audio will change after alignment. Do not use this feature if you plan to export the audio for use with the original video, such as multi-track audio on platforms like YouTube. The timing will no longer match the original footage. # Bulk Uploading Source: https://www.vozo.ai/docs/translate_dub/bulk_uploading Upload and translate multiple videos at once to streamline your workflow. This feature is only available on the **Studio Plan** or higher. In the upload dialog, select multiple video files from your computer. After uploading, configure the project settings.\ Your configuration — including source language and target language — will be applied to all uploaded videos. If the source or target languages differ across videos, do not upload them together.\ Instead, upload them in separate batches to ensure correct translation. Once submitted, all uploaded projects will appear in your **Project History** tab. Vozo will process each file as a separate translation project. # Change Voice Source: https://www.vozo.ai/docs/translate_dub/change_voice Learn how to change the voice for a speaker in your translated video. Vozo automatically clones the original voice of each speaker in your video. If you prefer not to use the original voice, you can easily switch to another one using the **Change Voice** feature. Click on a target sentence to activate the toolbar, then select **Change Voice** to open the dialog box. Changevoicedialog Pn In the dialog, open the dropdown menu to choose a voice. Click **Choose More from Library** to browse additional options. You can upload an audio file or record a sample to clone a new voice and save it to your voice library. Once you've selected a voice, click **Confirm**. To update only the current sentence, uncheck “Apply change to all speeches of \[Speaker]”. To apply the voice to all lines from the same speaker, leave it checked. Click **Generate Speech** to regenerate the audio with the new voice. If the wrong voice is used because the speaker tag is incorrect, you don’t need to use **Change Voice**. Instead, click the speaker tag, select the correct speaker, and click **Generate Speech** to fix it. # Clone New Voice Source: https://www.vozo.ai/docs/translate_dub/clone_voice Learn how to clone a voice using an audio recording or uploaded file. Vozo allows you to clone a new voice and apply it to your translation projects. This is especially useful if you want to personalize the audio output or ensure consistency across multiple projects. Click on any target sentence to activate the toolbar, then click **Change Voice** to open the dialog box. In the dialog, open the dropdown menu and click **Choose More from Library**. Go to the **Cloned Voice** tab and select **Clone New Voice**. You can either upload an audio file or record your voice directly in the dialog. This audio sample will be used to train the cloned voice. Clonevoicedialog Pn Give your new voice a name and click **Clone My Voice**. Vozo will process the sample and generate a new voice profile, which may take a few minutes. Once the new voice is ready, it will appear in your voice library. You can check the box to apply it to all lines spoken by the same speaker, or uncheck it to apply the voice change to just the current sentence. Then click **Confirm** to apply the selected voice. Click **Generate Speech** to regenerate the audio with your newly cloned voice. If you're not satisfied with the current speaker's voice and want to re-clone it using segments from the project, use the [**Reclone**](/docs/translate_dub/reclone_voice) feature instead. # Edit Translations Source: https://www.vozo.ai/docs/translate_dub/edit_translation Learn how to edit translations and update dubbing using the Vozo Translation Editor. Translatedubtranslatedtext Pn Click on the translated text to activate editing. Make your changes to the text. Once the text is modified, the **Generate Speech** button will appear. Click it to generate a new dubbing for the segment. If you have multiple translations to adjust, you can complete all edits first and then click the **Generate Speech** button at the top of the Speech section to batch update the dubbing for all modified segments. # Enhance Emotion Source: https://www.vozo.ai/docs/translate_dub/emotion Add emotion to your dubbing segments for more expressive delivery. ## Overview Vozo automatically generates dubbing that replicates each speaker’s average tone, emotion, and speaking style. But if you want to fine-tune a specific segment to express more nuanced or heightened emotions, you can use the **Enhance Emotion** feature. ## How to Use Select the segment you want to enhance, then click the **Enhance Emotion** button. Choose one or more emotions that best match the intended tone. For more nuanced expressions, you can select multiple options — for example, *Excited* + *Surprised*. Click **Generate with Emotion**. After a short wait, you’ll receive three emotionally enhanced versions. Preview the options and select your preferred version. Click **Apply Selected Dubbing** to use it. If you’re not satisfied with the result, you can change the selected emotions and regenerate — or select **Current Version** to keep the original without consuming any points. Emotion enhancement requires additional processing power and will consume **1 point**. Emotiondialog Pn ## Limitations * Once an emotionally enhanced dubbing is applied, clicking **Update Dubbing** or **Redub** will replace it with a standard version that does not retain emotional effects. Make sure both the speaker and translation are finalized before enhancing emotion. * The **Enhance Emotion** feature is not compatible with **Add Pause**. If your translation includes pause markers, they will not be reflected in the enhanced dubbing. * The dubbing preview will use a standard speed. You can adjust the speed on the timeline after applying. * This feature may be less effective for extreme emotions such as intense crying or screaming. ## FAQ Currently, emotion enhancement must be applied one segment at a time. Batch processing is not supported. # Get Started Source: https://www.vozo.ai/docs/translate_dub/get_started Translate & Dub allows you to effortlessly localize video content, including voice, subtitles, and lip sync. ## Create a Project To get started, navigate to your **Dashboard** and click on **AI Translation - Translate & Dub**. This will open the upload dialog, where you can drag and drop your video/audio files or click to upload. You can also paste a link to upload your video. Before processing your video, you’ll need to configure a few project settings: 1. **Original Language**: Select the original language of your content. 2. **Translated to**: Choose the target language you want your video translated into. 3. **[Voice Cloning Model](/docs/translate_dub/voice_model):** Choose the appropriate voice cloning model based on your content type. If you're not sure which one to use, select Auto. 4. **Number of Speakers**: Specify the number of speakers in the video/audio. If unsure, select Auto for automatic detection. For better accuracy, we recommend selecting the exact number of speakers if you know it. 5. **Add / Replace Subtitles in Video:** Enable this toggle to add translated subtitles to your video. If your video already contains original subtitles, you can also choose “Add & Remove Original Subtitles” to replace them. 6. **[Auto-Adjust Video Speed for Alignment](https://www.vozo.ai/docs/translate_dub/auto_align_audio_video):** When enabled, video speed is adjusted segment by segment within a reasonable range to align with the dubbed audio, to keep playback smooth and natural. 7. **Advanced Settings** (Optional): * **Translation Prompt**: Choose a preset or enter tone, background, or language style preferences to guide translation. * [**Glossary**](/docs/common/glossary): Select one or more glossaries to define how key terms should be translated and pronounced. * **[Use Existing Subtitles](/docs/translate_dub/use_existing_subtitles):** Toggle this on to use your own subtitles or transcript and skip transcription or translation. 8. **Proofread Before Dubbing** (Optional): Enable this to open the [Proofreading Editor](/docs/translate_dub/proofreading-editor) before dubbing begins, so you can verify speakers, original text, and translations before the dub is generated. Once you have configured your settings, click **Start Translate** to begin. ## Proofreading Transcription and Speaker After your translation and dubbing are complete, you can easily proofread and correct the [transcription and speakers](/docs/translate_dub/proofread) using Vozo Translation Editor. Simply click on the incorrect original text to edit it, or click on the incorrect speaker tag to switch to the correct speaker. After making the corrections, click the **Generate Speech** button to refresh the dubbing. Translateduboriginaltext Pn ## Edit Translations You can manually [edit the translation](/docs/translate_dub/edit_translation) by clicking on the text to activate editing. After making changes, click the **Generate Speech** button to generate new dubbing for the segment. Translatedubtranslatedtext Pn You can also have the [**AI Pilot**](/docs/translate_dub/ai_pilot) help you edit the translations. ## Adjust Audio Timing and Speed Due to differences in language structure, the duration of the translated audio may differ from the original. Vozo's automatic translation ensures the audio aligns as closely as possible while maintaining a natural speaking pace. * **Adjust Timing**: Click on the audio clip you want to adjust, then drag it left or right on the timeline. Adjusttiming Gi * **Adjust Speed**: Hover over the left or right edge of the audio clip to reveal the control handle. Drag the handle to adjust the speed of the clip. These adjustments take effect immediately and can be previewed directly in the editor. Adjustspeed Gi ## Add Subtitles & Lip Sync The automatically translated video includes the new dubbing. You can enhance it further by adding translated subtitles or performing lip sync if needed. ### Add Subtitles 1. Click on the **Subtitles Tab** on the left. 2. Toggle the **Add Subtitle** switch. It will take a few minutes to generate the subtitles. 3. Once generated, you can modify their style as needed. ### Lip Sync 1. Click on the **Lip Sync Tab** on the left. 2. Configuration options are explained in [Get Started with Lip Sync](/docs/lipsync/get_started). Once configured, start lip sync to create a lip sync project. Lip-sync is based on creating a new lip-sync project for the current video. Ensure the translated audio is accurate and finalized before starting lip-sync. ## Export and Download If you're satisfied with the video, click the **Export** button in the top-right corner of the editor. Once the export is complete, click the **Download** button to download the video file. ## FAQ Please refer to the [Points Usage for AI Tools](/docs/common/tools-points-rules) page for detailed pricing rules. # Lip Sync Source: https://www.vozo.ai/docs/translate_dub/lip_sync Learn how to apply lip sync to a translated video after proofreading and dubbing are completed. ## Before You Start Before starting lip sync, make sure: * Your translation and dubbing are finalized. * The video contains one or more real people with clearly visible mouths. * Subtitles (if added) do not cover the speaker's mouth area. ## Apply Lip Sync 1. Click the **Lip Sync** tab in the left panel of the **Video Translation Editor**. 2. Configuration options are explained in [Get Started with Lip Sync](/docs/lipsync/get_started). Once configured, start lip sync to create a lip sync project. 3. For lip sync editing and advanced controls, see [Lip Sync Editor](/docs/lipsync/edit_lipsync). # Multi-language Translation Source: https://www.vozo.ai/docs/translate_dub/more_language Translate your video into multiple languages in one go — without repeating edits or speaker corrections. Vozo allows you to translate a video into multiple languages **in one go**, saving you time and effort. Instead of translating and editing each language version separately, you can **first finalize one primary translation**, then use it as the base to generate others. This ensures consistency in transcription, speaker tags, and timing — and avoids repeating the proofreading and speaker labeling steps for each target language. Start by creating a translation project in one target language (e.g., English to French). Make sure your original transcript and speaker tags are fully reviewed and accurate. This version will serve as the base for translating into additional languages. Click the **More Languages** button in the top-right corner of the **Speech** section for that project. Choose the additional languages you want to translate into. Vozo will use your edited transcript and speakers to generate all selected versions **in one go**. Context & Preference: This section will automatically populate with the Context & Preference you entered when the current project was created. * You can modify it here, and the changes will apply to all new translation tasks created later. * Make sure the context is general enough for all languages. For example, if you're translating into German, French, and Chinese, avoid something specific like “Translate into a serious German advertisement video” and use something more general, such as “Translate into a serious advertisement video in the target language.” Each new language will be created as a separate project in your Dashboard. You can review the translations for each language and make adjustments if needed. # Edit Original Text Source: https://www.vozo.ai/docs/translate_dub/proofread Learn how to correct the original text and edit segments in Vozo Translation Editor. When you upload a video in **Translate & Dub**, Vozo automatically generates the original text based on the audio and assigns a speaker label to each segment. The original text is the foundation for translation and dubbing. However, the original text may occasionally include errors — such as misrecognized words or incorrect speaker tags — which can lead to inaccurate translations or mismatched voices. It's important to review and correct these issues before continuing. ## Edit the Original Text ### Correct Word Errors 1. Click on the incorrect original text to activate editing. Translateduboriginaltext Pn 2. Correct the original text, and the **Retranslate** button will appear. Click it to retranslate the segment based on your updates. If multiple segments have errors, you can make all corrections first, then click the **Retranslate** button at the top of the Speech section to batch retranslate all corrected segments. 3. Once you receive the new translations, click **Generate Speech** to refresh the dubbing for these segments. You can click the **AI Pilot** at the bottom right of the Speech section and input prompts such as “Find Voza and replace it with Vozo in the original script.” to correct errors in the original text, such as names or brand terms. ### Add a Segment > If a sentence wasn’t recognized — for example, due to low volume or speaker overlap — you can manually add it as a new segment. Addsegment Pn 1. Hover between two segments and click the **"\\+"** button to add a new segment, or press **Enter** at the end of a segment to create one below. 2. Enter the missing original text and click the **Retranslate** button. ### Split a Segment Sometimes, you may need to split a segment (e.g., if two people's dialogue is recognized as the same speaker). Splitsegment Pn 1. Select part of the original sentence you want to split, or place the text cursor at the point where you want to divide it. 2. Click the **Split Segment** button on the toolbar, or press **Enter** in the middle of a segment to split it. (If the original sentence belongs to a different speaker, remember to update the speaker tag accordingly.) 3. Click **Retranslate** at the top to retranslate both segments. ### Merge Segments You might need to merge segments if a single sentence was incorrectly split into two. Mergesegments Pn 1. Hover your cursor between the two segments you want to merge and click the **Merge** button that appears, or press **Backspace** at the beginning of a segment to merge it with the one above. 2. After the segments are merged into one, click **Retranslate** to generate a new translation. ## Correct the Speakers If your video includes multiple speakers, the system will automatically differentiate between them. However, if you notice an error in speaker identification (which may cause the wrong voice to be used during dubbing), you can correct it. Learn how speakers work and how to edit speaker tags in our [Speaker Guide](/docs/translate_dub/speaker). # Proofread Before Dubbing Source: https://www.vozo.ai/docs/translate_dub/proofreading-editor Review and edit speakers, original text, and translations before generating your dub. This feature is only available on the Studio plan and above. Before dubbing, you can optionally proofread your translation to verify accuracy, correct speakers, and assign voices before the dub is generated. ## Enable Proofreading When creating a project, check **Proofread before dubbing** below the **Start Translation** button. Once translation is complete, the Proofreading Editor will open before dubbing begins. Image ## Review and Edit The editor displays your speakers, original text, and translated text side by side. You can: * Correct speaker labels and reassign segments to the right speaker * Edit the original text to trigger a re-translation of that segment * Edit the translated text directly without changing the original Image ## Speed Up Your Review The video panel on the right shows a popover overlaid on the video, displaying the original text recognized for that moment. You can play the video directly in this panel to quickly verify the content without switching between views Image To proofread even faster, use the playback speed selector next to the play button at the bottom of the video panel. Options include 1.5x, 2x, and 3x. Image ## Assign Voices Click the **Voice** tab on the left to review and update the voice assigned to each speaker. Each speaker's voice can be changed to one of the following: * **Clone voice from original speaker** — clones the speaker's voice directly from the original video * **Select from Voice Library** — choose an AI voice or a previously saved cloned voice from your libr Image ## Start Dubbing When you are satisfied with the review, click **Start Dubbing** in the top-right corner to proceed. # Reclone Voice Source: https://www.vozo.ai/docs/translate_dub/reclone_voice Improve voice quality or emotional tone by recloning the speaker's voice. Vozo automatically clones voices using all available speech segments from the original video, but sometimes the result may lack clarity or emotional tone. Recloning lets you handpick better voice samples for a more natural and refined output. Click any segment spoken by the target speaker, then click the **Change Voice** button in the toolbar that appears. Choose **Reclone the Voice**, then select the lines that best match the tone you're aiming for. Reclonedialog Pn Choose **Reclone the Voice**, then select the lines that best match the tone you’re aiming for. You can click the **Preview Voice** button to listen to the new voice before applying it. To update only the current sentence, uncheck “Apply change to all speeches of \[Speaker]”. To apply the new voice to all of the speaker’s lines, leave it checked. Click **Generate Speech** to update the voice in your video. # Simultaneous Speech Source: https://www.vozo.ai/docs/translate_dub/simultaneous-speech Dub multiple speakers talking at the same time within a single segment. Simultaneous Speech lets you assign multiple speakers to a single segment so their voices are merged into one audio clip when speech is generated. This is useful for moments where multiple people speak at the same time, such as when a group says something in unison. ## Enable Simultaneous Speech Click the speaker tag on a segment to open the **Change Speaker** dropdown. Click the **Select Multiple Speakers for Simultaneous Speech** icon in the top-right corner of the dropdown. A **Multi-Speaker Segment** dialog will appear. Image Check the speakers you want to include. Their voices will be merged into one audio clip when speech is generated. Image Click **Confirm**. The speaker tag on the segment will update to show the number of selected speakers, and the segment will be highlighted to prompt you to generate speech. Image ## Switch Back to Single Speaker Click the speaker tag on a multi-speaker segment to reopen the **Multi-Speaker Segment** dialog. Deselect all but one speaker and click **Confirm**. # Correct Speakers Source: https://www.vozo.ai/docs/translate_dub/speaker Learn how speaker tags work in Vozo, when to edit them, and how to improve voice results by managing speakers effectively. ## What Are Speakers? Vozo automatically assigns speaker tags (e.g., Speaker 1, Speaker 2) based on voice characteristics. These tags help distinguish each person’s lines for translation, dubbing, and voice cloning. Speakertag Pn ## How Speakers Are Detected Vozo automatically identifies different voice timbres to distinguish between speakers. While detection is automatic, you can manually correct tags if needed. ## When to Manually Correct Speakers Update or adjust speaker tags in these cases: * Speaker identification errors, such as one speaker being identified as another, one speaker being split into multiple, or multiple speakers being merged into one. * A speaker’s voice varies dramatically in emotion (e.g., calm vs. angry). For lines with a distinct emotional tone, create a **new speaker** to help Vozo generate a more appropriate cloned voice. ## How to Add or Edit Speakers For the segment you want to fix, click the current speaker tag. Choose the correct speaker from the dropdown, or click **New Speaker** to add a new one. Once all corrections are made, click **Generate Speech** in the **top right corner** to apply the changes. A new cloned voice will be created for any newly added speakers. ## Simultaneous Speech If multiple speakers say the same line at the same time, you can assign them to a single segment so their voices are dubbed as an overlapping mix. See [Simultaneous Speech](/docs/translate_dub/simultaneous-speech) for details. ## Tips for Managing Speakers * Rename Speakers: In the **Change Speaker** dropdown, click the edit icon next to a speaker to rename it (e.g., "Host", "Narrator", "Guest"). Renaming makes the speakers in your project easier to identify at a glance. Image * Filter Speaker: Use the **Filter** tool at the top-left of the Speech section to isolate all segments from a specific speaker for batch preview or editing. Speakerfilter Pn * Clear Speakers: Click the **Clear Speaker** icon in the top-right corner of the **Change Speaker** dropdown to remove any speakers that are no longer assigned to any segment. This is useful after extensive editing to keep the speaker list clean. Image ## FAQ Double-check that the speaker tags are correct. If everything looks good but the voice still feels off, you can use the [Reclone Voice](/docs/translate_dub/reclone_voice) feature to generate a better result. Currently, **speaker tags are project-specific**, meaning each project detects and assigns speakers independently.
However, if you've cloned a voice for a speaker, you can **save it to your Library** and reuse it in other projects for consistent audio performance. # Speed, Volume, Pitch Source: https://www.vozo.ai/docs/translate_dub/speed_volume_pitch Customize speed, volume, and pitch of translated audio clips. You can fine-tune the **speed**, **volume**, and **pitch** of translated audio to better match the tone and pacing of your video. Locate the timeline at the bottom of the page, then click on the translated audio clip you want to adjust. Click the **Speed/Volume/Pitch** button at the top-left of the timeline.\ In the popover, adjust the settings as needed. To apply the changes to all speeches by the same speaker, check **Apply change to all speeches of \[Speaker]**. Once you close the popover, the changes will take effect automatically. You can also stretch or shrink the audio clip directly in the timeline to adjust its speed. Adjustspeed Gi These adjustments only apply to translated audio clips. Original audio cannot be modified. # Using Existing Subtitles or Script Source: https://www.vozo.ai/docs/translate_dub/use_existing_subtitles Use your own subtitles or transcript to skip transcription or translation. ## Overview You can provide your own subtitles or transcript to replace part of the default workflow. * If you upload original subtitles or transcript, the system skips transcription and directly uses your text for translation. * If you upload translated subtitles, the system skips translation and directly generates dubbing from your text. ## How to Use After uploading your media file in Translate & Dub, click **Advanced Settings** and turn on **Use Existing Subtitles**. Select one of the following options: ### Option 1: Upload Subtitle File Use this option if you already have a subtitle or script file. Upload an SRT, VTT, or TXT (SRT-like) file with proper subtitle formatting and accurate timestamps, then choose how to use it: * **Use as original script**: skip transcription and use it for translation * **Use as final translated script**: skip translation and use it for dubbing Use Existing Subtitles #### Example ```text SRT/TXT theme={null} 1 00:00:01,000 --> 00:00:03,500 Hello there. 2 00:00:04,000 --> 00:00:07,000 Hi, Alice. How are you? ``` ```text VTT theme={null} WEBVTT 00:00:01.000 --> 00:00:03.500 Hello there. 00:00:04.000 --> 00:00:07.000 Hi, Alice. How are you? ``` ### Option 2: Extract from Video Use this option if subtitles are embedded in the video. Select this option and adjust the box to fully cover the subtitle area. * Only extracts original subtitles and does not support translated subtitles. * Only supports detecting embedded subtitles in English and Chinese * Only supports subtitles in a fixed position. ## Assign Speakers If your subtitle or script file includes speaker labels, Vozo will assign speakers during processing based on the speakers you define. This helps preserve speaker identity and ensures more accurate dubbing results. ### How to Add Speaker Labels Use the following format to define speakers in your file: * Add a speaker tag at the **beginning of each subtitle block** * Use the format: `` ### Example ```text SRT/TXT theme={null} 1 00:00:01,000 --> 00:00:03,500 Hello there. 2 00:00:04,000 --> 00:00:07,000 Hi, Alice. How are you? ``` ```text VTT theme={null} WEBVTT 00:00:01.000 --> 00:00:03.500 Hello there. 00:00:04.000 --> 00:00:07.000 Hi, Alice. How are you? ``` ### Rules and Limitations * Each subtitle block (cue) supports **only one speaker** * The speaker tag must appear at the **start of the first line** * All lines in the same block will be assigned to that speaker * Do not include multiple `` tags in the same block * If multiple speakers are needed, split them into separate subtitle blocks * If some subtitle blocks include `` tags while others do not, all unlabeled blocks will be treated as the same additional speaker. ### What Happens After Upload * During processing, Vozo assigns speakers based on your file * In the editor, speaker names will appear exactly as defined in your file * This also applies when using the API with subtitle upload # Voice Cloning Models Source: https://www.vozo.ai/docs/translate_dub/voice_model Learn the difference between VoiceREAL and VoiceNATIVE. ## Overview Vozo provides two voice cloning models in **Translate & Dub**: * **VoiceREAL** * **VoiceNATIVE** Both models preserve the original speaker’s voice identity, but they are optimized differently. | Feature | VoiceREAL | VoiceNATIVE | | ------------------------------ | ---------------------------------------------------------- | --------------------------------------------------------------------------------- | | Emotional delivery & tone | ★★★★★ | ★★★☆☆ | | Natural target-language accent | ★★★☆☆ | ★★★★★ | | Best for | Creator & personality-driven content | Explanatory & professional content | | Recommended for | Short Drama, Vlogs, Youtuber videos, entertainment content | Ads, UGC ads, tutorials, e-learning courses, product explainers, corporate videos | If you are unsure which model to use, select **Auto**. Vozo will automatically choose the most suitable model. ## How to Select a Model Before generation, select your preferred model under **Voice Cloning Model**. Select Voice Model ## FAQ No. The voice cloning model cannot be changed after generation. When a project is created, the selected voice cloning model is written into the project configuration. All future generations and regenerations within that project will continue using the same model. To use a different model, you need to: 1. Re-upload the video or audio 2. Select the correct voice cloning model 3. Submit a new translation project Voice cloning models only apply to cloned voices. If you select a system-provided preset voice from Voice Library, the voice will speak based on the languages and accents supported by that voice itself. It is not affected by the voice cloning model selected in your project. If you select a voice that you previously cloned, the voice will generate speech using the voice cloning model selected in your current project. Newly added languages will use the same voice cloning model used in the original project. If the original project was set to **Auto**, the newly added languages will follow the model that Auto ultimately selected for that project. For example, if the original project used **Auto** and Vozo determined that **VoiceREAL** was the most suitable model, then newly added languages will also use **VoiceREAL**. If you want to use a different model for the new languages, please re-upload the video or audio and submit a new translation project. For text translation, Vozo will use vocabulary, expressions, and speaking styles that match the selected regional variant. However, for dubbing, VoiceREAL preserves the original speaker’s accent and vocal characteristics. The generated voice may still sound closer to the original speaker’s accent rather than a fully native British English accent. If you want a more natural localized accent, we recommend using **VoiceNATIVE**. # Get Started Source: https://www.vozo.ai/docs/translate_subtitles/get_started Learn how to translate your video subtitles and customize them using Vozo's Translate Subtitles tool. ## Create a Project To get started, navigate to your **Dashboard** and click on **AI Translation - Translate Subtitles**. This will open the upload dialog, where you can drag and drop your video files or click to upload. You can also paste a link to upload your video. Before processing your video, you’ll need to configure a few project settings: 1. **Original Language**: Select the original language of your video. 2. **Translated to**: Choose the target language you want your video translated into. 3. **Subtitle Display**: Select whether to add **Translated Subtitles** only or **Original + Translated bilingual subtitles**. 4. **Remove Original Subtitles:** Turn this on to remove any original subtitles from the video. 5. **Advanced Settings** (Optional): * **Translation Prompt**: Choose a preset or enter tone, background, or language style preferences to guide translation. * **Glossary**: Select one or more glossaries to define how key terms should be translated. Only available for **Studio** and higher-tier plans. For more details, see [Glossary](/docs/common/glossary). * **Use Existing Subtitles:** Toggle this if your video already has accurate subtitles. You can upload a subtitle file or extract embedded subtitles from the video. Extraction currently supports English and Chinese only. ## Edit Subtitles Once the translation is complete, you can review and edit subtitles in Vozo's subtitle editor. If any translation errors occur due to incorrect source recognition, click the problematic original text, make your edits, and then click the **Retranslate** button above the segment to generate a new translation. You can also manually edit the translated text as needed. Translatesubtitleeditor Pn ## Modify Line Breaks Vozo automatically splits lines based on semantics. You can further split, merge, insert, or delete lines as you prefer, similar to editing a document: * **Split Line**: Click anywhere in a sentence and press **Enter** to split it into two lines at the cursor position. * **Merge Lines**: Click at the start of a sentence and press **Backspace** to merge it into the previous line. * **Insert New Line**: Click at the start or end of a sentence and press **Enter** to create a new line. Enter text to add subtitles. * **Delete Line**: Select the entire sentence and press **Backspace** to remove the text, then press Backspace again to delete the line itself. ## Adjust Subtitle Timing On the timeline, you can drag any subtitle clip to adjust its display time. ## Subtitle Display Above the video preview, you can choose the subtitle display mode: * **Translated Subtitle Only**: Show only translated subtitles. * **Original + Translated**: Display subtitles in both languages. ## Customize Subtitle Style Click the **Style** tab on the left panel. Here you can customize subtitle styles. If **Subtitle Display** is set to **Original + Translated**, you can individually customize the **Original Subtitles** and **Translated Subtitles**, or set them to **Use the Same Style**. If you want to change the maximum number of lines (for example, switch from 1 line to 2 lines), adjust the **Max Number of Lines** setting. Vozo will automatically re-break lines based on semantics. Other style changes will not trigger re-breaking. Translate Subtitle Style Pn ## Export and Download If you’re satisfied with the video, click the **Export** button in the top-right corner of the editor. Once the export is complete, click the **Download** button to download the video file. You can also download the **subtitle file** separately here. ## FAQ Please refer to the [Points Usage for AI Tools](/docs/common/tools-points-rules) page for detailed pricing rules. # Changelog Source: https://www.vozo.ai/docs/updates/changelog See what's new in Vozo — feature releases, improvements, and bug fixes. ## Subtitle Options for the Translate & Dub API * The Translate & Dub API now supports subtitle options for adding translated subtitles and removing original subtitles from output videos. ## AI Pilot in Proofreading * AI Pilot is now available in the Translate & Dub Proofreading editor to review and revise both original and translated text. ## Expanded Video Link Upload Support * Video uploads by link now support additional platforms, including X and Facebook. ## Automatic Interface Language * The Vozo interface now automatically switches based on the browser language. ## Faster Clip Navigation * Use the Up Arrow and Down Arrow keys in Translate & Dub to quickly play the previous or next clip. ## Bug Fixes * Fixed an issue where translating into English (Hong Kong) could fail. ## Expanded Support for Proofread Before Dubbing * Proofread before dubbing is now available when using Translate to More Languages in Translate & Dub. * The Translate & Dub API now also supports Proofread before dubbing. ## Visual Translate Improvements * Improved OCR processing to reduce residual duplicate subtitles. * Improved recognition and motion handling for animated callout text. ## Bug Fixes * Fixed issues that could cause audio speed adjustments or exports to fail. * Fixed an issue where only the last voice was used when translating a speaker assigned multiple voices into additional languages. * Fixed issues where regenerating split translations could produce outdated audio data or an incorrect segment order. * Fixed issues where OCR recognition or one-click alignment could create overlapping source subtitle timings. ## WeChat Pay in China * Added WeChat Pay as a payment method for users in China. ## Vozo Skills for AI Agents Skills * Vozo Skills let users run video localization workflows through natural-language requests to an AI agent, using Vozo CLI to connect the agent to Vozo for project creation, progress tracking, and result downloads without requiring users to learn commands. * Vozo Skills support AI Dubbing, Translate Subtitles, Visual Translate, and Lip Sync, including multi-language and batch workflows. * Learn more in the [Vozo Skills docs](/docs/ai-agent/skill). ## Proofread Before Dubbing Improvements * Subtitle downloads during proofreading now include both the source and translated SRT files. * Retranslating a block now requires its context to be translated at the same time, preventing potential dubbing failures. ## Translate & Dub Improvements * Improved the stability of translating individual segments. * Improved upload reliability with automatic retries and resumable transfers. ## More Accurate Visual Translate * Improved bullet point detection for more accurate text removal. ## Bug Fixes * Fixed potential subtitle position differences between the editor preview and exported video when exporting on a slow connection. * Fixed issues with keyboard shortcuts, splitting segments, and editor stability in Translate & Dub. * Fixed an issue where refreshing the page during dubbing in a Proofread Before Dubbing project could cause processing to fail. * Fixed an issue where stylized text could shift vertically in Visual Translate exports. * Fixed an issue where video retiming could fail when the selected range contained no video frames. ## More Natural Translations * Translations now use more natural, conversational phrasing. * Improved translation of interjections and conversational expressions to preserve the original tone more accurately. ## Faster, More Reliable Visual Translate * Text recognition is now twice as fast, with improved stability across videos. * Improved extraction of stylized text and handling of text segmentation and merging, reducing duplicate or overlapping translations. * Improved animated text removal with smoother OCR region tracking. ## Localized Display Formats * Improved localized formatting for dates and points across the interface. ## Bug Fixes * Fixed an issue where Vietnamese speech could read large numbers, such as 2,000,000, one digit at a time. * Fixed an issue where some multilingual translation projects could remain stuck in Processing. ## Visual Translate API * Supports creating and exporting Visual Translate projects through the API. [View API Reference →](https://www.vozo.ai/docs/api_reference/endpoints/visual_translate/overview) ## Visual Translate Improvements * Supports translating an existing Visual Translate project into additional languages without creating a new project. * Improves text alignment for translated on-screen text, resulting in more accurate placement and a more consistent visual layout. ## Subtitle Punctuation Control Adds a new subtitle punctuation setting that lets you control whether periods are displayed at the end of subtitle lines. ## Bug Fixes * Fixes an issue where point usage was calculated incorrectly when translating a speed-adjusted Translate & Dub project into additional languages. * Fixes an issue where pronunciation and pauses could be incorrect when dubbing into Simplified Chinese while displaying the translated text in Traditional Chinese. * Fixes an issue in Voice Studio where some text was incorrectly detected as Indonesian (`su-ID`), causing generation to fail. ## Visual Translate: Smoother Typewriter Tracking * Improves tracking of typewriter-style text animations, enabling more accurate removal of original on-screen text. ## Non-Speech Detection: More Accurate Recognition * Enhances accuracy of non-speech recognition — interjections and screams in ASR output are now more reliably split into dedicated non-speech blocks. ## VoiceREAL: Better Chinese Voice Quality * Improves Chinese voice quality and emotional expressiveness in the VoiceREAL model. ## Translate & Dub: Proofreading Editor Adds an optional proofreading step before dubbing to help verify translation accuracy before the dub is generated. Available to Studio plan users and above. To enable, check **Proofread Before Dubbing** below the Start Translate button when creating a project. * Displays speakers, original text, and translated text side by side for review * Allows assigning a specific voice from your voice library or saved cloned voices to each individual speaker * Overlays original text on the video preview for easier reference * Supports high-speed playback of the original video during proofreading, such as 2x or 3x [Learn more →](https://vozo.ai/docs/translate_dub/proofreading-editor) ## Translate & Dub: Simultaneous Speech Supports dubbing multiple speakers talking at the same time within a single segment. In the Change Speaker dropdown, click the **Select Multiple Speakers for Simultaneous Speech** icon to select more than one speaker for a segment. When generating speech, all selected speakers' voices will be used simultaneously. [Learn more →](https://vozo.ai/docs/translate_dub/simultaneous-speech) ## SRT Import Supports importing edited SRT files back into Translate & Dub and Translate Subtitles, useful for teams that proofread or edit captions outside of Vozo before finalizing. Click the **Import** button in the top-right corner of the editor to get started. ## Remove Unused Speakers * In Translate & Dub, if there are speakers that are not assigned to any segment, you can now remove them directly from the **Change Speaker** popover by clicking the **Clear** button in the top-right corner. ## Eyedropper & Color Palette Eyedropper Color Palette * Visual Translate now supports **Eyedropper** and **Color Palette** when editing text colors, making it easier to match colors from the original video. ## Extended Lip Sync Support for High-Resolution Videos * For videos above 1080p resolution, the maximum supported duration for Lip Sync has been increased from 10 minutes to 40 minutes. ## New Voice Cloning Model: VoiceNATIVE VoiceNATIVE * Introduces VoiceNATIVE, a new voice cloning model that delivers a natural target-language accent without carrying over the phonetic traits of the source language — optimized for ads, e-learning courses, and explainer videos * Adds a voice cloning model selector with three options: VoiceREAL (the original model), VoiceNATIVE (the new model), and Auto (automatically recommends the best fit when you're unsure which to choose) — [see the full model comparison](https://www.vozo.ai/docs/translate_dub/voice_model) ## 66 New Target Languages Added — Now Supporting 165 Total * See the [full list of supported languages](https://www.vozo.ai/docs/supported_languages) * Adds regional Arabic variants for Algeria, Bahrain, Iraq, Jordan, Kuwait, Lebanon, Libya, Morocco, Oman, Qatar, Syria, Tunisia, United Arab Emirates, and Yemen * Adds Assamese, Bangla, Gujarati, Marathi, Odia, and Punjabi * Adds seven regional Chinese variants: Guangxi, Jilu, Northeastern, Southwestern, Wu, Henan, and Shaanxi (all Simplified) * Adds eight regional English variants: Hong Kong, Kenya, New Zealand, Nigeria, Philippines, Singapore, South Africa, and Tanzania * Adds Inuktitut in both Latin and Syllabics scripts * Adds 21 regional Spanish variants across Latin America and the United States * Adds Swahili for Kenya and Tanzania * Adds Tamil for India, Malaysia, Singapore, and Sri Lanka * Adds Urdu for India and Pakistan ## Bug Fixes * Fixes subtitle segmentation for Burmese, Khmer, and Lao * Fixes an issue where Translate & Dub projects failed during lip sync processing * Improves Chinese speech recognition accuracy ## Expanded Target Language Support * Translate & Dub now supports 25 additional target languages: Afrikaans, Albanian, Armenian, Azerbaijani, Burmese, Georgian, Icelandic, Irish, Kannada, Kazakh, Khmer, Lao, Latvian, Lithuanian, Malayalam, Maltese, Mongolian, Persian, Serbian, Sinhala, Somali, Sundanese, Urdu, Uzbek, and Welsh. * Translate Subtitles adds the same 25 target languages. * Visual Translate now supports 30 additional target languages: Afrikaans, Albanian, Arabic (Egypt), Arabic (Saudi Arabia), Armenian, Azerbaijani, Burmese, Georgian, Hebrew, Icelandic, Irish, Kannada, Kazakh, Khmer, Lao, Latvian, Lithuanian, Malayalam, Maltese, Mongolian, Pashto, Persian, Serbian, Sinhala, Somali, Sundanese, Urdu, Uzbek, and Welsh. * All translation features now uniformly support 99 target languages. See the full list in the [Supported Languages docs](https://www.vozo.ai/docs/supported_languages). ## Subtitle Remover * Translate & Dub and Translate Subtitles can now remove burned-in subtitles from the source video. * In Translate & Dub: enable Add Translated Subtitles in Video, then choose **Add & Remove Original**. * In Translate Subtitles: toggle **Remove Original Subtitles** switch. * Learn more in the [Subtitle Remover docs](https://www.vozo.ai/docs/common/remove-original-subtitles). Subtitles Remove Demo ## Model Improvements & Bug Fixes * Upgraded the ASR model used for translation, reducing missed words and improving transcription coverage. * Fixed potential audio pops in background tracks. * Fixed potential audio pops at the end of generated speech. * Fixed potential text overlap in Visual Translate. ## Visual Translate: Project-Level Font Settings * Supports setting a unified font for the entire project in **Advanced Settings**. You can select **Custom Font** to define the font used across all translated text, with options to choose from preset fonts or upload your own. * Supports applying a selected font to all text in the project by clicking the **Apply** button after editing a text element in the editor. ## Translate & Dub: Assign Speakers from Subtitles * Supports specifying **Speaker** when uploading subtitle files in **Advanced Settings**, so speakers are assigned according to your input during processing. * Learn More: [Using Existing Subtitles as a Script](https://www.vozo.ai/docs/translate_dub/use_existing_subtitles#assign-speakers) ## Translate & Dub API: Glossary Support * Supports specifying `glossary_ids` in the API to guide translation and ensure more accurate terminology usage. * Learn More: [API Reference](https://www.vozo.ai/docs/api_reference/endpoints/translate_dub/create#body-glossary-ids) ## Translate & Dub Updates * Improved sentence segmentation: Fixed an issue where abbreviations like “Mr.” could incorrectly split a sentence into multiple segments. This has been resolved for several major languages. ## API Updates * API projects available in dashboard: You can now create projects via API and access them in the dashboard for further editing. To enable this, set `project_mode` to editable when creating a project. See the [API Reference](https://www.vozo.ai/docs/api_reference/endpoints/translate_dub/create#body-project-mode) for request details. ## Visual Translate Improvements * Enhanced motion handling for on-screen text: Beyond simple In and Out animations, Visual Translate can now preserve movement and scaling animations throughout the entire video. Motion对比 * Extended video length: Maximum video length increased from 5 minutes to 20 minutes. * 13 new source languages: Arabic, Bulgarian, Greek, Thai, Ukrainian, Urdu, Marathi, Tamil, Kazakh, Macedonian, Mongolian, Nepali, Cantonese. ## Translate & Dub Improvements * Added Find and Replace to search and update text across the entire project. ## Visual Translate Improvements * Maximum video length increased from 5 minutes to 20 minutes. * Added motion tracking for on-screen text, supporting movement and scaling, with automatic replication in translated results. ## AI Translation Updates ### Faster Speech Generation for Translate & Dub * Improved the speed of Generate Speech and Regenerate Speech, reducing wait times, especially for single segments. ### Same-Language Translation Support * Removed the restriction that source and target languages must be different. You can now translate into the same language and select a different locale. ## Translate & Dub Updates ### New Feature: Auto Align Audio & Video Auto Align Audio&video * Automatically adjusts video and audio speed segment by segment to keep them aligned, solving mismatch issues caused by different dubbing lengths across languages. * Two ways to apply this feature: * Enable after uploading your video: Go to Advanced Settings and enable the Auto-Adjust Video Speed for Alignment switch. * Apply in editor: After finishing dubbing edits, click the Auto Align Audio & Video button on the timeline to align. * Note: The overall duration of both video and audio will change after alignment. Do not use this feature if you plan to export audio for use in the original video. ### Editor Improvements * Support Segment Split, Merge, and Add with shortcuts: * Press Enter in the middle of a segment to split * Press Backspace at the beginning to merge with the segment above * Press Enter at the end of a segment to add a new one below * Support skipping retranslation: Click Skip Retranslation button after editing the original text to apply changes without retranslation. * Improve stability of the translation editor when editing long projects. * Improve interaction details and overall experience. ## Visual Translate Updates ### Support Embedded Subtitle Translation Embeddedsubtitletranslationnowsupported * Improved subtitle detection accuracy in Visual Translate, now enabling reliable translation of embedded subtitles in videos. ### Other Improvements * Improved text removal quality for on-screen text located near video edges. * Added support for Hindi as a source language. ## Translate & Dub Supports Downloading Background Audio * Click the Export button, expand the Audio category in the popover, and select Background Audio Only. ## Visual Translate Supports Exporting And Importing Original & Translated Text * Click the Export button and download Original & Translated Text as a TSV file. * The file can be used to review translation quality. * Click the Import button in the top-right corner to upload the edited file and update translated text. * Import supports TSV and TXT formats, but the original file structure must be preserved. ## Visual Translate Improvements * Added support to manually revert over-translated text and regenerate it * Added support to manually select missed text areas and regenerate translation * Added Russian and Korean as supported source languages ## Language Support Updates * Added Swiss German locale support under the German target language for Translate & Dub and Translate Subtitles ## API Support * Translate & Dub is now available via API. See the [API documentation](/docs/api_reference/endpoints/translate_dub/overview). ## Audio-Video Alignment Improvements * Improved audio-video alignment for better synchronization between dubbed audio and video in Translate & Dub ## Upload Support Updates * Audio uploads now support AAC format ## Visual Translate (Beta) * Launched **Visual Translate** beta. * Access via **Dashboard → AI Translation → Visual Translate**. * Detect explanatory on-screen text in video frames, remove the original text, and translate it into the target language. * Preserve original text position, layout, style, and animations, with support for manual edits. * Demo videos available for testing without consuming any points. * Fixed known issues from the Alpha version and improved overall results. * Now available to all users. Visual Translate Cover ## Visual Translate Alpha Improvements * Fixed bugs, improved stability, and enhanced output quality. ## Visual Translate Alpha Launch * Initial Alpha release. * Available to a limited group of users for internal testing. ## Pricing Updates * Updated plan names: Premium is now Creator, and Business is now Studio. * Subscription plans no longer support point-tier selection. Two new plans are available: Studio XL and Studio XXL. * The Pro plan is no longer available for new purchases. Existing Pro subscribers can continue renewing, but once canceled, the plan cannot be resubscribed after expiration. * If subscribed users run out of points, they can purchase one-time Points Packs to top up. Points Packs are valid for 1 year. * Local currency pricing is now supported, including USD, EUR, and JYP. The currency is determined by the user’s IP at the time of the first purchase, and all future renewals and payments will follow the same currency. ## VoiceLITE Retirement * The VoiceLITE model in Translate & Dub has been retired. * Due to adjustments on our voice service provider’s side, VoiceLITE is no longer available after this date. ## Use Existing Subtitles as Final Script * Translate & Dub and Translate Subtitles now support using uploaded subtitle files as the final translated script. * After uploading a subtitle file in Advanced Settings, you can choose: * Use as original script * Use as final translated script ## Japanese UI Support * Vozo now supports Japanese UI. Click the avatar in the top-right corner and select **Language** to switch to Japanese. ## Translation Duration Extension * For **Studio** and higher tiers, the maximum duration for a single Translation project has been extended from 60 minutes to 120 minutes. ## Auto Alignment Improvement * Improved Auto Alignment in Translate & Dub so the dubbed audio length matches the original more accurately and no longer plays noticeably shorter. ## Other Translation Improvements & Fixes * Fixed punctuation and formatting issues when translating from Chinese to Japanese. * Optimized subtitle timestamping for Thai source videos. * Bug fix: Resolved incorrect target language output when translating from fa-IR to ar. ## UI Enhancements * Set AI Translation as the first option in the Dashboard’s top feature cards for easier access. * Improved UI components across the product for better consistency and usability. * Redesigned the website homepage and updated the sign-up page. ## Project Search * Added Dashboard search, allowing you to find projects by keywords in the project name. ## Lip Sync Editor Interaction Improvements * Added Show Original & Mark Speaker toggle. * Turn it on to view the original and generated videos side by side. This makes it easier to spot incorrect lip sync or misidentified speakers and quickly correct them before regenerating. * Learn more: [Lip Sync Editor →](https://docs.vozo.ai/lipsync/edit_lipsync) Lip Sync Editor Show Original Pn ## New Feature: Create Variants * Upload a new audio to your existing **Lip Sync** or **Talking Photo** project to generate a new variant. * The model from your current project is reused to keep the same lip-sync accuracy and visual quality. * Generation is faster, and you’ll save 5 base points compared to creating a new project. Create Variants Pn **Learn More:** * [Lip Sync → Create Variant with New Audio](https://www.vozo.ai/docs/lipsync/variants) * [Talking Photo → Create Variant with New Audio](https://www.vozo.ai/docs/talking_photo/variants) ## API Update: Reusable LipSync API * We now support **Reusable LipSync API**. * The Reusable LipSync API is an optimized version of our LipSync API, designed for developers who frequently generate lip-synced videos using the same visual reference. [View API Reference →](https://www.vozo.ai/docs/api_reference/endpoints/reusable_lipsync/overview) ## Translate & Dub Editor Improvements * New: Support bulk selecting segments to Change Speaker, Revert to Original Audio, or Delete Segment * Ask AI now shows history of the last 3 custom prompts * Moved Revert to Original Audio button into the toolbar when original text is selected * Add Pause now supports a 0.2s option * Modified segments are now highlighted in a more noticeable yellow * Other interaction and UI polish ## Translation Pipeline Improvements * Upgraded the translation pipeline for **Translate & Dub** and **Translate Subtitles** * Enhanced translation accuracy and system stability ## Thai Language Support * Thai is now supported as the **original language** in **Translate & Dub** and **Translate Subtitles** (previously only supported as a **target language**) ## Other Updates * Introduced a new video preview page for VoiceREAL dubbing; you can enter the editor from the preview page or by clicking **Edit** on the project card in the Dashboard * Optimized project data loading on the Dashboard for smoother performance * Fixed known bugs ## Voice Studio Voice Studio Cover Pn * The original **Edit Script & Dub** tool has been officially renamed to **Voice Studio** * Now supports editing speech in uploaded audio files and creating voice-over from scratch * Pricing has changed from using dubbing tokens to point-based billing by generated speech duration — see [Points Usage for Speech Generation](/docs/common/speech-points-rules) for details ## Other Updates * Improved UI and interaction flow * Fixed issues with translation failures, incorrect speaker detection, and export errors * Optimized video rendering stability in some cases ## Fixes and Improvements * Fixed an issue where words were broken in the middle when wrapping in editor input fields * Fixed incorrect duration detection when uploading videos via TikTok URL * Improved performance and fixed other known issues ## Pricing Updates * Premium Plan updated: \$19/100 points → \$29/150 points monthly; \$180/1200 points → \$264/1800 points yearly. * Existing subscribers stay on old plans until renewal; if points run out, upgrading is required to get more immediately. * New Pro Plan introduced: \$8/month or \$72/year, includes all non-point features (no points included). * See full details on the [Pricing page](https://app.vozo.ai/pricing). ## Translate & Dub Updates * Points usage reduced from 10 points/min → 3 points/min, so the same points can now translate more content. * Editing dubbing in the editor now deducts points (3 points/min) based on the new audio length; regenerating without edits remains free. * Two voice models are now available: * VoiceREAL: our original high-quality model with expressive dubbing and full editing support. * VoiceLITE: newly introduced model, requires no points, but offers simpler one-shot results with weaker emotion. * See full comparison in [Voice Model](/docs/common/voice-models). ## Lip Sync Model Improvements * Enhanced sync accuracy * Better handling of faces with beards ## Other Updates * Added Chinese (Taiwan) to Translation Locale options * When creating a Lip Sync project from Translate & Dub, the project name now automatically includes the translation language * Fixed timestamp errors in longer Spanish videos * Fixed other known bugs ## Multi-Faces Lip Sync Price Halved * You no longer need to pay double for videos with multiple faces. * Lip Sync now costs the same as single-face videos: 5 points base + 5 points/min. ## Other Updates & Improvements * Improved Talking Photo model to fix occasional frame drops. * Enhanced emotion and tone consistency when using specified Accent in Translate & Dub. * Fixed several known bugs. ## Upgraded Multi-Faces Lip Sync Model * Upgraded multi-faces lip sync model for faster speed and more stable results. * When a video has more than one face to sync, the model will automatically sync the speaking faces without requiring face detection or face selection. You can still modify synced faces in the editor. ## Points Usage History Points Usage History Cover Pn * You can now view, filter, and export point usage from **Points Usage History** in the top-right avatar menu. ## Other Updates and Improvements * Changed project completion notification from browser-based to email-based. * Improved generation speed for Update Dubbing and Redub when subtitles are enabled in Translate & Dub. * Fixed known bugs. ## Lip Sync Generation Mode Selection Removed * Removed Generation Mode selection from Lip Sync and Talking Photo project settings * Projects now use Precision Mode by default ## Subtitle Translation Updates (Now Official Release) * Added option to display only original subtitles — configurable in the video preview area of the editor * Support translating from an existing project into more languages without re-uploading or re-proofreading (Studio+ plans) * Timeline clips now snap automatically when dragged * Support sharing projects with team members (Studio+ plans) * Optimized subtitle editing for better stability * Other performance improvements and bug fixes ## Other Improvements * Fixed popping noise issue when generating audio clips in Translate & Dub * Other performance improvements and bug fixes ## Audio Translation Audio Translation Cover Pn * Translate & Dub tool supports uploading audio files. ## Other Updates & Improvements * Updated UI on the sign-up page. * Improved translation quality for more accurate and stable results. * Fixed audio volume mismatch between preview and exported files in Translate & Dub. * Fixed other known bugs. ## Updates & Improvements * Removed the minimum video duration limit for Translation. * Translate & Dub: Now supports dubbing with uploaded translated subtitle files. Upload via Transcribe Original Audio > Upload Subtitle File when creating a project to skip transcription and translation. * Launched [Creator Rewards](https://www.vozo.ai/creator-rewards) and [Affiliate Program](https://www.vozo.ai/affiliate-marketing-program). * Face Swap videos are now stored for 30 days only. * Improved Lip Sync Precision Mode for single-speaker videos. ## Brand Template Updates * Live preview of intro/outro inside the editor * Intro and Outro now support custom images and duration settings * Support adjusting logo opacity * Undo and Redo now available when editing brand template settings * Support selecting a saved Brand Template when creating a Translate & Dub project ## Translation: Expanded Language & Locale Support Amharic, Basque, Bengali, Bosnian, Catalan, Estonian, Galician, Hebrew, Hungarian, Javanese, Macedonian, Nepali, Norwegian Bokmål, Pashto, Slovenian, Swahili, Telugu, Zulu * Arabic: Egypt, Saudi Arabia * Chinese: Mainland China, Hong Kong * Dutch: Belgium, Netherlands * English: Australia, Canada, India, Ireland, United Kingdom, United States * French: Belgium, Canada, France, Switzerland * German: Austria, Germany, Switzerland * Portuguese: Brazil, Portugal * Spanish: Mexico, Spain ## Improved ASR Accuracy for Translation ASR models have been upgraded for improved transcription accuracy in some source languages. English (United States, Australia, United Kingdom, Canada, Ghana, Hong Kong, Ireland, Kenya, Nigeria, New Zealand, Philippines, Singapore, Tanzania, South Africa), Spanish (Spain, United States, Mexico, Argentina, Bolivia, Chile, Colombia, Costa Rica, Cuba, Dominican Republic, Ecuador, Equatorial Guinea, Guatemala, Honduras, Nicaragua, Panama, Peru, Puerto Rico, Paraguay, El Salvador, Uruguay, Venezuela), Portuguese (Brazil, Portugal), French (France, Belgium, Canada, Switzerland), German (Germany, Austria, Switzerland), Italian (Switzerland, Italy), Russian (Russia), Japanese (Japan), Hindi (India), Turkish (Turkey), Finnish (Finland), Czech (Czech Republic), Danish (Denmark), Dutch (Belgium, Netherlands), Polish (Poland), Romanian (Romania), Slovak (Slovakia), Swedish (Sweden), Indonesian (Indonesia), Bulgarian (Bulgaria), Greek (Greece), Malay (Malaysia), Ukrainian (Ukraine), Catalan (Spain), Galician (Spain), Kannada (India), Macedonian (North Macedonia), Malayalam (India), Norwegian Bokmål (Norway), Serbian (Serbia), Vietnamese (Vietnam), Filipino (Philippines), Hungarian (Hungary), Tamil (India), Bengali (India), Bosnian (Bosnia and Herzegovina), Gujarati (India), Kazakh (Kazakhstan), Latvian (Latvia), Lithuanian (Lithuania), Marathi (India), Nepali (Nepal), Slovenian (Slovenia), Persian (Iran) ## Other * Fixed known bugs. ## New Feature: Glossary Glossary Pn * Ensure consistent translation and pronunciation of key terms with custom glossaries. * Glossary only works with Translation tools, including Translate & Dub and Translate Subtitles. Learn more in the [Glossary Guide](/docs/common/glossary). ## New Feature: Subtitle Translation (Beta) Subtitle Translation Cover Pn * Add translated subtitles to your video, or choose bilingual subtitles (original + translated). Learn more in the [Subtitle Translation Guide](/docs/translate_subtitles/get_started). # Roadmap Source: https://www.vozo.ai/docs/updates/roadmap A preview of what's in progress and what's coming soon to Vozo. * **Voice Selection Before Dubbing:** Choose a specific voice from your Voice Library before creating a Translate & Dub project. * **Hide All Subtitle Punctuation:** You can choose to hide all punctuation marks in subtitles. * **Bulk Export:** Export videos from multiple projects at once. * **All-in-One Translation:** Complete dubbing and on-screen text translation within a single workflow. * **AI Glossary:** Automatically generate glossary terms from your existing files or translation projects using AI. # Dubbing After Visual Translate Source: https://www.vozo.ai/docs/visual_translate/continue_dub This article explains how to continue localizing the audio part of a video after completing visual text translation. After exporting a video from **Visual Translate**, you can continue processing it by going to the **Dashboard** and clicking **AI Translation**, then selecting the tool you need. ## Translate & Dub **Translate & Dub** is used to localize the spoken audio in videos, such as voiceovers or dialogue. It automatically: * Translates the original speech * Generates dubbed audio in the target language using the original speaker’s voice * Optionally adds subtitles or continues with lip sync Use this tool if you want to handle dubbing, subtitles, or lip sync in one place. ## Translate Subtitles **Translate Subtitles** is designed for subtitle-only workflows. It allows you to generate translated subtitles or bilingual subtitles without changing the original audio. If you want to keep the original voice and only translate subtitles, use this tool. ## Upcoming Improvements We’re working on integrating visual text translation, audio translation and dubbing, subtitle translation, and lip sync into a single one-click workflow—stay tuned. # Export and Import a Text File Source: https://www.vozo.ai/docs/visual_translate/export_import_text Learn how to export and import text in Visual Translate. This feature allows you to export Visual Translate text as a file, review or edit it externally, and import it back to update translations in bulk. ## Export Text You can export a file containing the **original text**, **timestamps**, and **translated text**. There are two ways to download the file: 1. Click **Export**, then select **Original & Translated Text** in the popover menu. Visual Translate Download Text 2. Click **Import**, then download the TSV file from the import dialog. The downloaded file includes: * Original text * Start and end timestamps * Translated text After exporting the file, you can review and modify the translations as needed. ## Edit the File After reviewing or editing the translations, save the file as **TSV** or **TXT** format. Keep the file structure unchanged. Modifying the structure may cause the import to fail. ## Import the File In the editor, click **Import** in the top-right corner. Upload the edited **TSV** or **TXT** file. Visual Translate Import Text The system will update the project based on the file content. ## Import Requirements ### Timestamp Format The **end time** must be later than the **start time**, and the timestamp format must remain valid. ### Project Status Restrictions Importing is not allowed in the following situations: * Some segments are processing **Retranslating** * Some segments are in **Pending Regenerate** status Please wait until processing is complete before importing the file. ## How the System Updates Your Project After importing the file, the editor will update the project according to these rules: 1. **Update translations**\ If the translated text is modified, the system updates the translation. 2. **Update original text**\ If the original text is modified, the system updates the original text. 3. **Update timestamps**\ If the timestamps are modified, the system updates the segment timing. 4. **Add new entries**\ If new rows are added, the system creates new text segments using the default style. You can adjust the style in the editor. 5. **Deleted rows**\ If rows are removed from the file, the corresponding text will not be deleted automatically. To remove text, delete it manually in the editor. # Get Started Source: https://www.vozo.ai/docs/visual_translate/get-started Visual Translate helps you translate on-screen text in videos, such as slides and explanatory overlays, while preserving layout, style, and animations. ## What Is Visual Translate Visual Translate translates on-screen text in videos, including slides, captions, and explanatory overlays. It focuses on visual elements rather than spoken audio. ## Create a Project To get started, navigate to your **Dashboard** and click on **AI Translation - Visual Translate**. Upload a video file to begin. Please make sure the video is suitable for this feature. For supported types and scenarios, see [Supported Video Types](/docs/visual_translate/supported_types). Before submitting the translation, configure the following settings: 1. **Original Language**: Select the language of the on-screen text in the video. 2. **Translated to**: Choose the target language. 3. **Advanced Settings** (Optional): * **Translation Prompt**: Provide tone, style, or context to guide the translation. * **Glossary**: Apply one or more glossaries to control term translation and consistency. Once ready, submit the project and wait for processing to complete. ## Preview and Edit Translations After processing, you’ll enter the editor to review and edit the results. ### Compare View You can preview the video in **side-by-side view**, comparing: * The original video * The translated video This helps you quickly verify accuracy and layout consistency. Visual Translate Compare View ### Edit Text Content Select any text element in the video. All edits are made in the **right-side panel**. * **Edit text content**: * If the detected source text is incorrect, edit it and click**Retranslate** to regenerate the translation. * You can also directly edit the translated text. * **Adjust text style and animation:** * **Text Style**: Font, size, color, and other visual styles * **Animation**: In and Out animations * **Timing**: Start time, duration, and layer order Visual Translate Edit ### Edit Directly on Canvas You can also adjust text elements directly in the video preview: * Move text position * Rotate text * Resize the text box width Visual Translate Text Move ## Export the Video After reviewing and editing, click the **Export** button in the top-right corner to generate the final video. ## Continue with Dubbing, Subtitles, or Lip Sync If you want to continue with **dubbing**, **subtitles**, or **lip sync**, export the video first and then upload it to the corresponding tool. We’re working on integrating Visual Translate with dubbing, subtitles, and lip sync into a single workflow. Stay tuned. ## FAQ Please refer to the [Points Usage for AI Tools](/docs/common/tools-points-rules) page for detailed pricing rules. # Revert to Original Source: https://www.vozo.ai/docs/visual_translate/revert_to_original Revert translated text back to its original state. ## When to Use This Feature During the Visual Translate process, some text may be translated even though it should remain unchanged. The **Revert to Original** feature allows you to revert those areas back to the original text from the source video. ## How to Revert Text to Original In the translated video canvas, click the text that should be reverted. In the right panel under the Text tab, click the **Revert to Original** button. Visual Translate Revert Button After clicking the button, the selected area will be highlighted with a frame, indicating it has been marked to revert. After reviewing the entire video and marking all areas that should be reverted, click **Regenerate Video** at the bottom of the editor and wait for the video to finish regenerating. Visual Translate Revert Regenerate ## Final Result After regeneration is complete, the marked text areas will revert to the original text and original style in the original video. # Supported Video Types Source: https://www.vozo.ai/docs/visual_translate/supported_types Learn which types of videos work best with Visual Translate, and which ones are not supported. ## Typical Use Cases ### Presentation / Slide-based Videos Videos where the main content is delivered through slides or presentation-style visuals. * **Educational and learning videos** 画面翻译对比2 * **Internal or external training videos** 画面翻译对比10 * **Briefings & analysis presentations** 画面翻译对比9 ### Live-action Videos with Simple On-screen Overlays Real-world footage accompanied by simple on-screen text, labels, or callouts. * **How-to videos (crafts, cooking, DIY)** 画面翻译对比6 * **Training videos (safety, setup, operation)** 画面翻译对比11 * **Product overview & instructional videos** 画面翻译对比 * **Interview videos** 画面翻译对比3 ## What Visual Translate Handles ### Text That Will Be Translated Visual Translate detects and translates **explanatory on-screen text** added to videos, which is intended to explain, guide, or annotate the video content. This includes: * Text on slides shown in videos 可以被翻译 * Text overlays added during video editing (excluding brand logos) 可以被翻译3 ### Text That Will Not Be Translated Text that is part of the **original visual material** of the video, and is not intended as explanatory content, is not supported. This includes: * UI elements, such as software interfaces, buttons, or menus 不能被翻译 * Real-world text, such as packaging, signage, or text on physical objects 不能被翻译2 ### Supported Text Styles and Animations Visual Translate works best with text that has **simple styling and animations**. **Well-supported** * Plain text or text with basic styling (e.g. solid color text, simple outlines, drop shadows, or a basic background color) * Static text or lightly animated text (e.g. fade in/out, simple slide in/out) **Limited support** * Text with heavy visual effects or special styling (e.g. glow effects, 3D text, distorted text, or text with varying colors or sizes for emphasis).\ In these cases, Visual Translate may not fully reproduce the original styling and will simplify the text to a more basic appearance. * Text with complex animations (e.g. continuously moving, rotating, or transforming).\ While the system attempts to match the original placement and timing, complex motion may result in incomplete removal of the original text or visual misalignment. # Translate Missed Text Source: https://www.vozo.ai/docs/visual_translate/translate_missed_text Detect and translate text that was missed during the initial Visual Translate process. ## When to Use This Feature During the automatic translation process, some on-screen text may not be detected or translated. The **Translate Missed Text** feature allows you to manually select these missed areas so the system can detect the text, remove the original content, and generate translated text. ## How to Translate Missed Text Hover over the translated video area, then click the **Translate Missed Text** button in the top-right corner. Visual Translate Translate Missed Text A Frame will appear on the screen. Resize or move the frame to cover the text that was not detected during the initial translation. If multiple pieces of text were missed, you can include them within the same frame. Visual Translate Frame Missed Text Click Confirm Selection to submit the selected area. The system will start detecting text within the selected region. After detection is complete, the detected text will be highlighted with frames in the video. If some highlighted text should not be translated, select it and click **Cancel this change** to undo the selection. Once you have reviewed the entire video and confirmed all necessary areas, click **Regenerate Video** at the bottom of the editor, then wait for the video to be regenerated. Visual Translate Frame Text Regenerate ## Final Result After regeneration is complete: * The original on-screen text will be removed. * The translated text will appear in the video. * The translated text remains **editable**, allowing you to further refine the result if needed.