GET
/v1/schemas/mistral/audio/v1%2Faudio%2Fspeech
Accept:
Request body
11 properties · 1 required · 6 $defs| property | type | description | constraints |
|---|---|---|---|
| input* | string | Text to generate a speech from | |
| model | string | nullable | |
| metadata | MetadataDict | Custom type for metadata with embedded validation. | nullable |
| stream | boolean | default: false | |
| prompt_cache_key | string | nullable | |
| voice_id | string | The preset or custom voice to use for generating the speech. | nullable |
| ref_audio | string | string | The audio reference for generating the speech. | nullable |
| expressiveness | number | Speaker flow-matching classifier-free guidance scale. Must be finite and at least 1.0. | 1 ≤ n ≤ 5 · nullable |
| phoneme_hints | object | Optional pronunciation hints mapping a (case-sensitive) word to its ordered list of IPA phones. | nullable |
| conversation_history | SpeechUserTurn | SpeechAssistantTurn[] | Prior turns, oldest first, alternating and ending on a user turn: `input` is the assistant reply to it. Conditions delivery, not speaker: set `voice_id` to choose the speaker. Requires `voice_id` to be a preset voice whose `kind` is `pvc`. Cannot be combined with `ref_audio`. | nullable |
| response_format | enum | Output audio format. Defaults to mp3. | pcm | wav | mp3 | flac | opus |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"mistral","endpointId":"v1/audio/speech","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}