GET

/v1/schemas/cartesia/audio/stt

kind inputactivity audiohash 89bc99bb…extracted Oct 30, 2026version currentsource upstream spec ↗
fieldrecorded source
schemaSource linked above.

upstream-spec

Source trace
a9ce21d0a3b28a57ef89ece81b676ac90c24bd222b3d9e2a9c10d00b53fe8205
{
  "fetchedAt": 1793337635,
  "extractorVersion": "1",
  "verifiedAt": null
}

Request body

4 properties · 2 required · 1 $defs
propertytypedescriptionconstraints
file*stringThere's no need to break up your audio file. Long files are intelligently chunked by our server.format: binary
model*enumID of the model to use for transcription. Must be in the `ink-whisper` family of models.ink-whisper
languageenumThe language of the input audio in ISO-639-1 formaten | zh | de | es | ru | ko · +94 more · default: "en"
timestamp_granularities[]TimestampGranularity[]

Types

1 $defs

TimestampGranularityenum

The granularity of timestamps to include in the response. Currently only `word` level timestamps are supported, providing start and end times for each word.

word

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", …}]}