> ## 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. # Translate text segments (sync) > Translate plain text segments in one request. Translated strings are returned immediately in the HTTP `data` payload. Does **not** process video or audio — use **Create translate and dub job** for media. ## OpenAPI ````yaml /api-reference/openapi.json post /openapi/v1/task/translate/create openapi: 3.1.0 info: title: VMEG Open API description: >- Integrate VMEG into your product: translate and dub video or audio, synthesize speech, clone voices, translate plain text, and manage API-side files. All responses use `{ code, message, data }`; `code === 200` means success. 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: >- Localize uploaded video or audio end-to-end: transcribe speech, translate the script, generate AI dubbing (cloned or preset voices), and return new dubbed media. Optional subtitles and lip sync. **Async only** — dubbed files arrive via [Webhook](/guides/webhooks). This is not plain text translation; see [Media translation](/guides/products/media-translation). - name: TTS x-group: Text to speech (TTS) description: >- Turn text into natural speech with preset or cloned voices. **Sync** returns audio URLs in the HTTP response; **async** delivers results via [Webhook](/guides/webhooks). See [Text to speech](/guides/products/text-to-speech). - name: Voice clone x-group: Voice cloning description: >- Create a reusable voice from a short reference recording. Returns a `voiceId` you can pass to TTS or translate-and-dub jobs. See [Voice clone](/guides/products/voice-clone). - name: Text translation x-group: Text translation (text only) description: >- Translate plain text segments — no audio or video processing. For spoken content in media files, use **Video & audio translate and dub** instead. See [Text translation](/guides/products/text-translation). - name: Task management x-group: Task status and history description: >- List, inspect, or delete jobs created through any product API. Poll `GET .../tasks/detail` when you cannot rely on webhooks. Scoped to your **API Key**. See [Products overview](/guides/products/overview). - name: Assets - Materials x-group: Upload files (materials) description: >- Upload and manage video/audio files used as input for translate-and-dub jobs. Flow: finish the full upload (presigned or multipart → register) → pass the registered `materialId` to create-async. See [Material upload](/guides/assets/material-upload). - name: Assets - Voices x-group: Voices (presets and clones) description: >- List preset voices for TTS, or manage voices you cloned. Cloned voices are created via **Voice cloning**. See [Voices](/guides/assets/voices). paths: /openapi/v1/task/translate/create: post: tags: - Text translation summary: Translate text segments (sync) description: >- Translate plain text segments in one request. Translated strings are returned immediately in the HTTP `data` payload. Does **not** process video or audio — use **Create translate and dub job** for media. operationId: translateCreateSync parameters: - $ref: '#/components/parameters/IdempotencyKeyRequired' requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/OpenApiTranslateCreateRequest' responses: '200': description: Success content: application/json: schema: $ref: '#/components/schemas/OpenApiTranslateCreateResponse' 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: OpenApiTranslateCreateRequest: type: object required: - language - segments properties: language: type: object required: - source - target properties: source: type: string example: zh-CN description: >- Source locale (BCP-47). See [Supported languages](/guides/supported-languages). target: type: string example: en-US description: >- Target locale (BCP-47). See [Supported languages](/guides/supported-languages). description: Source and target locales for translation segments: type: array maxItems: 50 items: $ref: '#/components/schemas/OpenApiTranslateSegment' description: Text segments to translate (max 50) options: $ref: '#/components/schemas/OpenApiTranslateOptions' description: Optional translation settings (context, scene, glossary, prompt) OpenApiTranslateCreateResponse: allOf: - $ref: '#/components/schemas/OpenApiResponseBase' - type: object properties: data: description: Translated segments returned in the synchronous HTTP response. allOf: - $ref: '#/components/schemas/OpenApiTranslateCreateData' OpenApiTranslateSegment: type: object required: - text properties: text: type: string description: Source text for this segment gender: $ref: '#/components/schemas/OpenApiTranslateSpeakerGender' description: 'Speaker gender for this segment. Enum: `male` or `female`.' speaker: type: string example: Speaker A description: >- Speaker label for multi-speaker content; helps keep pronouns and voice consistent across segments locale: type: string example: zh-CN description: Per-segment locale when it differs from `language.source` context: type: array items: type: string description: >- Per-segment neighbor lines. Takes priority over `options.sourceContext`; useful with `provided_only` when segments are not time-contiguous start: type: number description: >- Start time in seconds on the source timeline. Pair with `end` to mark this segment's time span for neighbor context end: type: number description: >- End time in seconds on the source timeline. Must be provided with `start` and be greater than or equal to `start` OpenApiTranslateOptions: type: object description: Optional translation settings properties: sourceContext: $ref: '#/components/schemas/OpenApiTranslateSourceContext' description: >- How to use surrounding source text. Defaults to `independent` when omitted sceneCustomized: $ref: '#/components/schemas/OpenApiTranslateSceneCustomized' description: Scene and delivery style hints glossary: type: object additionalProperties: type: string description: Term glossary map (source term → preferred translation) prompt: type: string description: Custom prompt appended to the translation instruction skipMissingTranslationCheck: type: boolean default: false description: >- When `true`, skip validation that every segment received a translation 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 OpenApiTranslateCreateData: type: object properties: taskId: type: string description: Open API task ID items: type: array items: $ref: '#/components/schemas/OpenApiTranslateResultItem' description: Translated segments, aligned with request segments by index createdAt: type: string description: Task creation time (ISO 8601) OpenApiTranslateSpeakerGender: type: string description: Speaker gender for a translation segment enum: - male - female example: male OpenApiTranslateSourceContext: type: object description: >- Global strategy for using neighbor context. Lower priority than per-segment `context` properties: mode: type: string enum: - independent - provided_only - neighbor default: independent description: >- `independent` — translate each segment alone. `provided_only` — use neighbor text supplied in segment `context`. `neighbor` — auto-pick neighbors from ordered segments using `contextWindow` contextWindow: type: integer minimum: 1 maximum: 20 default: 5 description: >- Only when `mode` is `neighbor`: number of segments before and after the current one to include (1–20) OpenApiTranslateSceneCustomized: type: object description: Scene-specific translation behavior properties: scene: type: string enum: - video - audio - subtitle - voiceover default: video description: Content type hint for the translation model allowStutter: type: boolean default: true description: >- Whether disfluencies (stutters) in the source may be preserved in the translation OpenApiTranslateResultItem: type: object properties: text: type: string description: Translated text errorMessage: type: string description: Failure reason when translation failed for this segment securitySchemes: apiKeyAuth: type: http scheme: bearer description: >- Send your API Key in the **`Authorization`** header (`Bearer `). See [Authentication](/guides/authentication). ````