Audio modelActive
Voxtral Mini TTS
Mistral AI
- Released
- -
- Data date
- September 24, 2026
- Model class
- Languages
- Access
Voxtral Mini TTS combines text-to-speech with zero-shot voice cloning. A voice sample is enough for the voice prompt, and Mistral says no transcript of that sample is required. The model supports nine languages and produces first audio in about 90 ms during streaming according to the provider. This combination defines the endpoint for voices that need to start quickly from a clone.
Mistral lists the Voxtral Mini TTS weights under CC BY-NC 4.0. The license applies whether the checkpoint runs locally or through the API. API access and local weights are separate access paths, but neither bypasses the non-commercial terms.
Specifications and access
| Specification | Value and source |
|---|---|
| Model class | Text-to-speechSource |
| Access | API and local executionSource |
| API model ID | voxtral-mini-tts-2603Source |
| Input | Text and voice sampleSource |
| Output | AudioSource |
| Task | Speech generation and voice cloningSource |
| Supported details | Nine languages and zero-shot voice cloningSource |
| Weights license | CC BY-NC 4.0Source |
| Languages | 9 languagesSource |
| Time to first audio | About 90 ms when streamingSource |
Popularity
20.4 / 100
Published prices
- Speech generation price
- $16 per 1M charactersSource
Sources and data date
| Type | Evidence and data date |
|---|---|
| Additional source | Mistral model documentation (retrieved September 24, 2026) · Mistral AI Voxtral TTS model page · Editorial description reviewed October 2, 2026 |
| Additional source | OpenRouter: Popularity index (derived), CC BY 4.0 |
| Additional source | Vercel AI Gateway: Popularity index (derived), CC BY 4.0 |
| Additional source | Creative Commons Attribution 4.0 |