GET

/v1/schemas/cohere/audio/v2%2Faudio%2Ftranscriptions

kind inputactivity audiohash 2fdf3af3…extracted Aug 15, 2026version currentsource upstream spec ↗

Request body

4 properties · 3 required · 0 $defs
propertytypedescriptionconstraints
model*stringID of the model to use.
language*stringThe language of the input audio, supplied in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639_language_codes) format.
file*stringThe audio file object to transcribe. Supported file extensions are flac, mp3, mpeg, mpga, ogg, and wav.format: binary
temperaturenumberThe sampling temperature, between 0 and 1. Higher values like 0.8 make the output more random, while lower values like 0.2 make it more focused and deterministic.

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"cohere","endpointId":"v2/audio/transcriptions","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}