GET
/v1/schemas/mistral/audio/v1%2Faudio%2Ftranscriptions
Accept:
Request body
11 properties · 1 required · 2 $defs| property | type | description | constraints |
|---|---|---|---|
| model* | string | ID of the model to be used. | |
| file | string | The 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_url | string | Url of a file to be transcribed | length ≥ 1 · length ≤ 2083 · format: uri · nullable |
| file_id | string | ID of a file uploaded to /v1/files | nullable |
| language | string | Language of the audio, e.g. 'en'. Providing the language can boost accuracy. | nullable |
| temperature | number | nullable | |
| stream | const | false · default: false | |
| diarize | boolean | default: false | |
| context_bias | string[] | default: [] | |
| speaker_references | object | Dictionary 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_granularities | TimestampGranularity[] | Granularities of timestamps to include in the response. |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"mistral","endpointId":"v1/audio/transcriptions","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}