> ## Documentation Index > Fetch the complete documentation index at: https://docs.vmeg.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create translate and dub job > Create a translate-and-dub job on the **same pipeline as vmeg.ai**. The first pass renders the dubbed output: poll [Query job status](/api-reference/app-synced/tasks/get-task-detail) until `status` is `finished`, then read `result.outputs[0]`. The job appears in **My tasks** on the website; open `editorUrl` to edit and re-export. Credits follow website pricing. Differences from Standalone: `options` is optional; `source` takes `materialId` or `youtubeUrl` (no `sourceUrl`); `taskType` must match the material (`vt` video, `at` audio); `title` sets the job name on the website; `output` and `extraData` are rejected with `400`; burned-in subtitles use `options.subtitle` instead of `text`; results are polled, not delivered by webhook. Other unknown fields are ignored. ## OpenAPI ````yaml /api-reference/app-synced.json post /openapi/v1/app/task/media-translation/create-async openapi: 3.1.0 info: title: VMEG Open API (App-Synced) description: >- Same protocol as the Standalone API, but every task, material, and cloned voice lives in your VMEG website account: jobs show up in **My tasks**, open in the editor, and can be re-exported. Poll `GET /openapi/v1/app/tasks/detail` for results (no webhooks). See [Standalone vs App-Synced](/guides/app-synced/comparison). Linked guides are written for the Standalone API. The steps are the same; use the `/openapi/v1/app` prefix instead of `/openapi/v1`. version: 1.0.0 servers: - url: https://api.vmeg.ai description: Production security: - apiKeyAuth: [] tags: - name: Media translation x-group: Video & audio translate and dub description: >- Translate and dub uploaded video/audio or a YouTube link on the same pipeline as vmeg.ai. The first pass renders the dubbed file; the job also appears in **My tasks** for editing and re-export. Poll [Query job status](/api-reference/app-synced/tasks/get-task-detail) for results. - name: Voice clone x-group: Voice cloning description: >- Clone a voice from a short recording. The voice is saved to **My voices** on the website and returned as `cv_*` for translate-and-dub jobs. - name: Task management x-group: Task status and history description: >- List, inspect, or delete the video/audio translation jobs in your VMEG account, including jobs created on the website. - name: Assets - Materials x-group: Upload files (materials) description: >- Upload and manage the files in your website material library (**My assets**). Finish the upload (single-file or multipart), then pass `materialId` to create-async. - name: Assets - Voices x-group: Voices (presets and clones) description: >- List preset system voices (`sv_*`) and manage your cloned voices (`cv_*`, same as **My voices** on the website). paths: /openapi/v1/app/task/media-translation/create-async: post: tags: - Media translation summary: Create translate and dub job description: >- Create a translate-and-dub job on the **same pipeline as vmeg.ai**. The first pass renders the dubbed output: poll [Query job status](/api-reference/app-synced/tasks/get-task-detail) until `status` is `finished`, then read `result.outputs[0]`. The job appears in **My tasks** on the website; open `editorUrl` to edit and re-export. Credits follow website pricing. Differences from Standalone: `options` is optional; `source` takes `materialId` or `youtubeUrl` (no `sourceUrl`); `taskType` must match the material (`vt` video, `at` audio); `title` sets the job name on the website; `output` and `extraData` are rejected with `400`; burned-in subtitles use `options.subtitle` instead of `text`; results are polled, not delivered by webhook. Other unknown fields are ignored. operationId: appMediaTranslationCreateAsync parameters: - $ref: '#/components/parameters/IdempotencyKeyRequired' requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/AppMediaTranslationCreateRequest' responses: '200': description: Task accepted. `editorUrl` opens the job in the website editor. content: application/json: schema: $ref: '#/components/schemas/AppMediaTranslationAcceptedResponse' components: parameters: IdempotencyKeyRequired: name: X-Idempotency-Key in: header required: true description: >- Required on mutating `POST` requests that create tasks or change persisted data (max 64 characters). See [Idempotency](/guides/idempotency). schema: type: string maxLength: 64 schemas: AppMediaTranslationCreateRequest: type: object required: - taskType - source - language properties: taskType: $ref: '#/components/schemas/AppTaskType' description: >- `vt` video translation | `at` audio translation. Must match the material type, otherwise `400`. source: $ref: '#/components/schemas/AppMediaTranslationSource' language: $ref: '#/components/schemas/OpenApiMediaTranslationLanguage' description: Source and target locales for localization options: $ref: '#/components/schemas/AppMediaTranslationOptions' title: type: string maxLength: 255 description: >- Job name shown in **My tasks** (max 255 characters). Defaults to the file name or the YouTube video title. AppMediaTranslationAcceptedResponse: allOf: - $ref: '#/components/schemas/OpenApiResponseBase' - type: object properties: data: allOf: - $ref: '#/components/schemas/OpenApiMediaTranslationAcceptedData' - type: object properties: editorUrl: type: string description: >- Website editor URL for this job (sign in with the same VMEG account) AppTaskType: type: string enum: - vt - at description: '`vt` video translation | `at` audio translation' AppMediaTranslationSource: type: object description: Exactly one of `materialId` or `youtubeUrl` properties: materialId: type: string description: >- Material ID from [App-Synced upload](/api-reference/app-synced/assets/materials/gen-upload-url) or [List materials](/api-reference/app-synced/assets/materials/list-materials) youtubeUrl: type: string description: 'YouTube video URL (use `taskType: vt`)' subtitleMaterialId: type: string description: >- Optional `.srt` material with the source-language subtitles. Other file types return `400`. targetSubtitleMaterialId: type: string description: >- Optional `.srt` material with the translated subtitles. Other file types return `400`. OpenApiMediaTranslationLanguage: type: object required: - target properties: source: type: string default: auto example: auto description: >- Source locale (BCP-47) or `auto` for detection. See [Supported languages](/guides/supported-languages). target: type: string example: zh-CN description: >- Target locale (BCP-47). See [Supported languages](/guides/supported-languages). description: Source and target locales for localization AppMediaTranslationOptions: type: object required: [] description: >- Pipeline options (all optional). Voice rules match the website: `voiceClone.style` picks automatic dubbing; `voiceSpeakers.selectedVoicesList` picks voices manually (`sv_*` system, `cv_*` your cloned voices) and cannot be combined with `voiceClone`. `dubbingVersion: V2` cannot be combined with either. Leave `voiceSpeakers.timbreMethod` empty when you set voices; a conflicting value returns `400`. properties: dubbingVersion: type: string enum: - V1 - V2 default: V1 description: >- Dubbing version, same as the website. `V1` (default): mature and reliable, auto-match a voice or choose one yourself. `V2`: more natural voices and richer emotions; it picks voices automatically, so it cannot be combined with `voiceClone` or `voiceSpeakers.selectedVoicesList`. subtitle: $ref: '#/components/schemas/AppMediaTranslationSubtitle' voiceClone: $ref: '#/components/schemas/AppMediaTranslationVoiceClone' transcribe: $ref: '#/components/schemas/OpenApiMediaTranslationTranscribe' translate: $ref: '#/components/schemas/OpenApiMediaTranslationTranslate' separation: $ref: '#/components/schemas/OpenApiMediaTranslationSeparation' dynamicVideoLength: $ref: '#/components/schemas/OpenApiMediaTranslationDynamicVideoLength' lipsync: $ref: '#/components/schemas/OpenApiMediaTranslationLipsync' description: >- Lip sync on the dubbed video. Requires width and height of at least 360 px, same as the website; lower-resolution materials return `400`. YouTube sources are not pre-checked; make sure the video is at least 360p. voiceSpeakers: $ref: '#/components/schemas/OpenApiMediaTranslationVoiceSpeakers' OpenApiResponseBase: type: object properties: code: type: integer example: 200 description: Business code; 200 means success message: type: string example: '' description: Human-readable detail when `code` is not success required: - code OpenApiMediaTranslationAcceptedData: type: object description: Immediate response for media translation async create (no deliverables) required: - taskId properties: taskId: type: string description: Task ID (same as the job ID on the website) taskType: $ref: '#/components/schemas/AppTaskType' status: type: string enum: - running - failed - finished example: running description: Task status after acceptance (`running`, `failed`, or `finished`) createdAt: type: string description: Task creation time (ISO 8601) AppMediaTranslationSubtitle: type: object description: >- Burned-in subtitles (video translation only). Omit to render without subtitles, same as the website default. Replaces the Standalone `text` field; sending `text` returns `400`. properties: type: type: string enum: - none - target - origin - multi description: >- `none` no subtitles | `target` translated | `origin` original | `multi` both. When omitted: `target` if `templateId` is set, otherwise `none`. Audio translation accepts only `none`. templateId: type: string description: >- Style from [List subtitle templates](/api-reference/app-synced/media-translation/list-subtitle-templates). When omitted, the website's default style (the first template in the list) is used. AppMediaTranslationVoiceClone: type: object required: [] description: Automatic dubbing settings (optional). Omit to use website defaults. properties: style: type: string enum: - emotional - consistent - auto - tutorial - drama - smart default: emotional description: >- `emotional` (default) | `consistent` clone the original voices; `auto` lets VMEG decide; `tutorial` / `drama` are content presets; `smart` matches preset voices. mode: type: string enum: - role - mix - sentence example: role description: >- role | mix | sentence. Only for `emotional` / `consistent`; optional. provider: type: string enum: - V1 - V2 - V3 - V4 - V5 description: >- Clone engine (`V1`–`V5`). Only for `emotional` / `consistent`; optional. See [Supported clone methods](/guides/supported-clone-methods). OpenApiMediaTranslationTranscribe: type: object description: Automatic speech recognition (ASR) settings properties: mode: type: string enum: - fast - normal default: fast description: ASR speed vs accuracy trade-off type: type: string default: default description: ASR profile (product default when omitted) OpenApiMediaTranslationTranslate: type: object description: Text translation step inside the media pipeline properties: mode: type: string enum: - default - machine default: default description: >- `default` — standard localization. `machine` — machine translation mode prompt: type: string description: Custom prompt for the translation step OpenApiMediaTranslationSeparation: type: object description: Source separation (vocals vs background) properties: mode: type: string default: auto example: auto description: Separation mode (e.g. `auto`) OpenApiMediaTranslationDynamicVideoLength: type: object description: Dynamic video length adjustment (video translation) properties: enable: type: boolean description: Enable dynamic length matching between source and dubbed video OpenApiMediaTranslationLipsync: type: object description: >- Lip sync (video translation only; may add credits). See [Pricing](/guides/pricing) properties: enable: type: boolean default: false description: Enable lip sync on the output video OpenApiMediaTranslationVoiceSpeakers: type: object description: Speaker and timbre configuration for dubbing properties: selectedVoicesList: type: array items: $ref: '#/components/schemas/OpenApiMediaTranslationSelectedVoice' description: Explicit voice picks per speaker slot speakerNum: type: string example: auto description: Number of speakers to detect (`auto` or a numeric string) timbreMethod: type: string enum: - clone - smart example: clone description: '`clone` — clone from source audio. `smart` — smart voice matching' OpenApiMediaTranslationSelectedVoice: type: object description: A preset or cloned voice selected for dubbing properties: provider: type: string example: S1 description: >- Optional preset tier (`S1`, `S2`, …) when you pick a system voice. Clone voices use `V1`–`V5`. See [Voices](/guides/app-synced/comparison). voiceId: type: string description: >- `sv_*` from [List system voices](/api-reference/app-synced/assets/voices/list-system-voices) or `cv_*` from [List cloned voices](/api-reference/app-synced/assets/voices/list-cloned-voices) securitySchemes: apiKeyAuth: type: http scheme: bearer description: >- Send your API Key in the **`Authorization`** header (`Bearer `). See [Authentication](/guides/authentication). ````