Our state-of-the-art text-to-speech model with zero-shot voice cloning. Supports 9 languages, streaming with ~90ms time-to-first-audio, and no transcript required for voice prompts.
function_calling| Model | Max duration | Sample rate | Channels | Languages | Genres |
|---|---|---|---|---|---|
| voxtral-mini-transcribe-3-0 | — | — | — | — | — |
| voxtral-mini-transcribe-realtime-3-0 | — | — | — | — | — |
| voxtral-mini-transcribe-realtime | — | — | — | — | — |
| voxtral-mini-tts-3-0 | — | — | — | — | — |
| voxtral-mini-tts | — | — | — | — | — |
| voxtral-mini | — | — | — | — | — |
| voxtral-small-transcribe-3-0 | — | — | — | — | — |
| voxtral-small | — | — | — | — | — |
| voxtral-tts | — | — | — | — | — |
/v1/models/mistral/voxtral-mini-tts-2603