Languages & Models
Supported language and model identifiers.
Languages
The service passes the language value straight through to the upstream STT endpoint. Use the language code expected by the upstream model.
Common examples:
zh— Chineseen— Englishauto— let the upstream auto-detect the language
Real-time, segment, and batch jobs all accept a language field. In the realtime gateway, update the language at any time with a session.update message.
Model and capability identifiers
model— offline STT model override (defaultwhisper-large-v3-turbo)sttModel/stt_model— realtime STT model selectionnormalizerModel/normalizer_model— text normalizer model selectionbackend— upstream backend selection
Not all model fields are forwarded by the gateway; see Session Configuration for the current whitelist.
Specific identifier values depend on the upstream provider and are not contractually fixed by this gateway.
See also
- Live Translation — source language, target language, auto-detection, and code-switching
- Segment Transcription — sync multipart parameters
- Batch Jobs — async
audio_urlparameters - Session Configuration — realtime
session.updatefields
Batch Transcription Jobs
Asynchronous batch transcription from audio_url (CF Workflow).
Errors
HTTP status codes, WebSocket error events, and error payload formats.
Resources
