Transcribe And Translate Audio
POST/openai/v1/audio/translations
Transcribe Bambara audio and translate the result.
Mirrors POST /v1/audio/translations, so client.audio.translations.create()
works unchanged. OpenAI's endpoint always targets English; Djelia defaults to
English and additionally accepts language="fra_Latn" for French, since French is
the pairing Bambara speakers most often want.
Billing: this endpoint runs two models, so it is charged for two: the transcription per second of audio, and the translation per character of the transcript, each at its own rate. They appear as two usage records against the same request. A translation that fails is not charged.
temperature reaches sunjata-1 only.
Ignored: prompt.
Request
Responses
- 200
- 400
- 401
- 402
- 404
- default
The translated transcript.
Invalid request
Invalid or missing API key
Insufficient balance
Unknown model or endpoint
Error