Transcribe audio
API Reference
Transcribe audio
Accepts either an absolute file path OR an audio_base64 + mime_type
pair. The engine + model can come from a saved mode_id, from explicit
engine/model/language fields, or a mix (mode supplies defaults
and per-call fields override).
POST
Transcribe audio
Authorizations
Token from the discovery file. Required on every endpoint except /health.
Body
application/json
Absolute filesystem path. Mutually exclusive with audio_base64.
base64-encoded audio bytes. Pair with mime_type.
e.g. audio/wav, audio/m4a, audio/mpeg, audio/flac
Saved Mode used as the baseline. May be combined with engine/model/language to override per-call.
whisperLocal | parakeet | qwen3Asr | appleSpeech |
