GET

/v1/schemas/cartesia/audio/stt?kind=output

kind outputactivity audiohash bc2b257a…extracted Aug 15, 2026version currentsource upstream spec ↗

Response body

7 properties · 2 required · 1 $defs
propertytypedescriptionconstraints
type*enumThe message type. Always `transcript` for a batch transcription response.transcript
text*stringThe transcribed text.
request_idstringUnique identifier for this transcription request.
is_finalbooleanNot used for batch transcription.deprecated
languagestringThe specified language of the input audio.
durationnumberThe duration of the input audio in seconds.format: double
wordsTranscriptionWord[]Word-level timestamps showing the start and end time of each word. Only included when `[word]` is passed into `timestamp_granularities[]`.

Validate a payload

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