> ## Documentation Index > Fetch the complete documentation index at: https://developers.phrase.com/llms.txt > Use this file to discover all available pages before exploring further. # Translate Recording > Add one or more target translation languages to a recording that already exists, without recreating the project. Use this instead of `POST /v1/projects` whenever the project already exists — for example the caller forgot a language at creation time, the user asks for another language later, or the caller only learns which language is needed after seeing the transcript. ## Precondition: source transcription must be complete Translation reads the recording's transcript, so it can only run after transcription has finished. This is **not enforced synchronously** by this endpoint — a call made too early is accepted and queued, but produces no usable result. Before calling this endpoint, check `GET /v1/recordings/{recordingId}/status?language={sourceLanguage}` and confirm `transcription` is `true` (or poll `GET /v1/recordings/{recordingId}/status?summary=true` until `status` is `COMPLETED`). ## Re-requesting a language A language already in the recording's translation languages is not skipped — it is retranslated (logged as a retranslation rather than an initial translation). Only include a language in `languages` if you actually want it (re-)translated; use `ignoredLanguages` to record a language as intentionally not translated without omitting it from tracking. ## Language support `languages` accepts any BCP-47-style code Phrase Studio has translation support for — effectively all locales except the literal `auto` placeholder. Do not pass the recording's own source language: the Studio UI excludes it from the language picker, but this endpoint does **not** reject it — it is accepted and produces a same-language "translation". An unsupported code is rejected with `400`. ## After translation completes Call `POST /v1/projects/{projectId}/recordings/{recordingId}/dubbing` to dub any of the resulting languages — dubbing requires the language to be translated first. ## OpenAPI ````yaml /openapi/phrase-studio.json post /v1/projects/{projectId}/recordings/{recordingId}/translate openapi: 3.0.3 info: title: Studio API description: >- API for creating projects and reading transcription, translation, and dubbing results. version: 1.0.0 servers: - url: https://api.studio.us.phrase.com description: Production US Environment - url: https://api.studio.eu.phrase.com description: Production EU Environment security: [] tags: - name: Projects description: Manage transcription, translation, and dubbing projects - name: Recordings description: Access recording status and output data - name: Subtitle Profiles description: Manage subtitle formatting profiles - name: Pronunciations description: Manage custom pronunciation rules - name: Glossaries description: Manage translation glossaries - name: Insights description: Manage AI-powered insight prompts - name: Safe Communications description: Access safe communication evaluation templates - name: Subtitles description: Write subtitle segments for a recording paths: /v1/projects/{projectId}/recordings/{recordingId}/translate: post: tags: - Recordings summary: Translate Recording description: >- Add one or more target translation languages to a recording that already exists, without recreating the project. Use this instead of `POST /v1/projects` whenever the project already exists — for example the caller forgot a language at creation time, the user asks for another language later, or the caller only learns which language is needed after seeing the transcript. ## Precondition: source transcription must be complete Translation reads the recording's transcript, so it can only run after transcription has finished. This is **not enforced synchronously** by this endpoint — a call made too early is accepted and queued, but produces no usable result. Before calling this endpoint, check `GET /v1/recordings/{recordingId}/status?language={sourceLanguage}` and confirm `transcription` is `true` (or poll `GET /v1/recordings/{recordingId}/status?summary=true` until `status` is `COMPLETED`). ## Re-requesting a language A language already in the recording's translation languages is not skipped — it is retranslated (logged as a retranslation rather than an initial translation). Only include a language in `languages` if you actually want it (re-)translated; use `ignoredLanguages` to record a language as intentionally not translated without omitting it from tracking. ## Language support `languages` accepts any BCP-47-style code Phrase Studio has translation support for — effectively all locales except the literal `auto` placeholder. Do not pass the recording's own source language: the Studio UI excludes it from the language picker, but this endpoint does **not** reject it — it is accepted and produces a same-language "translation". An unsupported code is rejected with `400`. ## After translation completes Call `POST /v1/projects/{projectId}/recordings/{recordingId}/dubbing` to dub any of the resulting languages — dubbing requires the language to be translated first. operationId: translateRecording parameters: - name: projectId in: path required: true description: Project ID schema: type: string format: uuid - name: recordingId in: path required: true description: Recording ID schema: type: string format: uuid requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/TranslateRecordingRequest' examples: add_translation_language: summary: Add Czech as a translation target language value: languages: - cs responses: '200': description: Translation started for the requested languages '400': description: Bad Request content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: bad_request: summary: Bad Request value: success: false statusCode: 400 message: Bad Request timestamp: '2025-01-01T00:00:00.000Z' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: unauthorized: summary: Unauthorized value: success: false statusCode: 401 message: Unauthorized timestamp: '2025-01-01T00:00:00.000Z' '403': description: Forbidden content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: forbidden: summary: Forbidden value: success: false statusCode: 403 message: Access denied timestamp: '2025-01-01T00:00:00.000Z' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: not_found: summary: Not Found value: success: false statusCode: 404 message: Project or recording not found timestamp: '2025-01-01T00:00:00.000Z' '500': description: Internal server error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: internal_server_error: summary: Internal server error value: success: false statusCode: 500 message: Internal server error timestamp: '2025-01-01T00:00:00.000Z' security: - apiKeyAuth: [] components: schemas: TranslateRecordingRequest: type: object required: - languages properties: languages: type: array items: type: string description: >- Target languages to (re-)translate. A language already present on the recording is retranslated, not skipped — only list a language here if you want it (re-)run. Any BCP-47-style code with translation support is accepted except the literal `auto` placeholder. Do not pass the recording's source language — the Studio UI excludes it from the picker, but this field does not reject it. ignoredLanguages: type: array items: type: string default: [] description: >- Subset of `languages` to record as intentionally not translated (tracked on the recording so it shows as deliberately skipped, not pending or failed) instead of actually running translation for it tmsProjectTemplateUid: type: string description: >- TMS project template to use if translation is routed through a connected TMS subtitleProfiles: type: object additionalProperties: type: string description: >- Subtitle profile id per language code. List available ids with GET /v1/subtitle-profiles. styleGuides: type: object additionalProperties: type: string description: >- Style guide id per language code. Style guides belong to a separate Phrase system (Frame), not Phrase Studio itself — no external Studio API lists them. termBases: type: object additionalProperties: type: array items: type: string description: >- Term base ids per language code. Term bases belong to a connected TMS, not Phrase Studio itself — no external Studio API lists them. ErrorResponse: type: object properties: success: type: boolean example: false statusCode: type: integer example: 400 message: type: string example: Bad Request timestamp: type: string format: date-time example: '2025-01-01T00:00:00.000Z' required: - success - statusCode - message - timestamp securitySchemes: apiKeyAuth: type: apiKey in: header name: X-API-Key ````