/audio/translationsCreate an audio translation
Translates an uploaded audio file into English. Supply file and model, then optionally control prompting, output format, and sampling temperature. The response contains translated text or a verbose translation object.
- RetriesRetries up to 2×, 500ms backoff, 30s timeout.
Multipart form data containing the audio file, translation model, and optional output and sampling settings.
One documented failure
slow_downYour request rate increased too quickly. Please reduce the request rate and gradually increase it again.
Traffic increased too quickly
One documented failure
server_is_overloadedThe model is temporarily overloaded. Please retry your request after a brief delay.
The requested model is temporarily overloaded
A 429 is returned when the request exceeds the rate limit, and a 503 is returned when the service or requested model is temporarily unavailable. file and model are required, model must be whisper-1, response_format must be one of the listed formats, and temperature must be between 0 and 1.