GET

/v1/schemas/openai/chat/realtime%2Ftranscription_sessions?kind=output

kind outputactivity chathash 7b7a92dfextracted Jul 6, 2026version currentsource upstream spec ↗

Response body

5 properties · 1 required · 1 $defs
propertytypedescriptionconstraints
client_secret*objectEphemeral key returned by the API. Only present when the session is created on the server via REST API.
modalitiesanyThe set of modalities the model can respond with. To disable audio, set this to ["text"].
input_audio_formatstringThe format of input audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.
input_audio_transcriptionAudioTranscriptionResponseConfiguration of the transcription model.
turn_detectionobjectConfiguration for turn detection. Can be set to `null` to turn off. Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech.

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"openai","endpointId":"realtime/transcription_sessions","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}