Create Translation | Mesh API Docs

Translate speech in any language to English text.

OpenAI-compatible POST /v1/audio/translations — the path the OpenAI SDK’s client.audio.translations.create() calls. Provider is resolved from the model name via model_pricing; the adapter must implement speech_to_text_translate() (providers that don’t → 422).

response_format: json (default) → {"text": "..."}; text → the raw transcript as text/plain; verbose_json → the per-word structure. All in English.

Translate speech in any language to English text. OpenAI-compatible `POST /v1/audio/translations` — the path the OpenAI SDK's `client.audio.translations.create()` calls. Provider is resolved from the model name via model_pricing; the adapter must implement `speech_to_text_translate()` (providers that don't → 422). `response_format`: `json` (default) → `{"text": "..."}`; `text` → the raw transcript as `text/plain`; `verbose_json` → the per-word structure. All in English.

Authentication

AuthorizationBearer

Bearer authentication of the form Bearer <token>, where token is your auth token.

Request

This endpoint expects a multipart form containing a file.

modelstringRequired

filefileRequired

promptstring or nullOptional

response_formatstring or nullOptional

temperaturedouble or nullOptional0-2

Response

Successful Response

textstring

Errors

422

Unprocessable Entity Error

$	curl -X POST https://api.meshapi.ai/v1/audio/translations \
>	-H "Authorization: Bearer <token>" \
>	-H "Content-Type: multipart/form-data" \
>	-F model="string" \
>	-F file=@string