GET

/v1/schemas/mistral/audio/v1%2Faudio%2Ftranscriptions

kind inputactivity audiohash 87f4e8d4…extracted Nov 5, 2026version currentsource upstream spec ↗

Request body

11 properties · 1 required · 2 $defs
propertytypedescriptionconstraints
model*stringID of the model to be used.
filestringThe File object (not file name) to be uploaded. To upload a file and specify a custom file name you should format your request as such: ```bash file=@path/to/your/file.jsonl;filename=custom_name.jsonl ``` Otherwise, you can just keep the original file name: ``…format: binary · nullable
file_urlstringUrl of a file to be transcribedlength ≥ 1 · length ≤ 2083 · format: uri · nullable
file_idstringID of a file uploaded to /v1/filesnullable
languagestringLanguage of the audio, e.g. 'en'. Providing the language can boost accuracy.nullable
temperaturenumbernullable
streamconstfalse · default: false
diarizebooleandefault: false
context_biasstring[]default: []
speaker_referencesobjectDictionary of speaker names and reference audios for speakers who are known to appear in the audio. When enabled, diarize must be true. Predicted speakers will be matched against reference speakers from this dictionary.
timestamp_granularitiesTimestampGranularity[]Granularities of timestamps to include in the response.

Validate a payload

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