Voxtral TTS
Voxtral TTS is a 4B-parameter text-to-speech model that generates expressive speech in nine languages. It supports low-latency generation and voice adaptation from a short reference, and is available through an API, Mistral Studio, Le Chat, and as open weights.
What it does
Use it to generate multilingual speech for voice agents, narration, or speech-to-speech translation systems.
- Availability
- Available now via API; test in Mistral Studio and Le Chat
- Pricing model
- $0.016 per 1k characters
- Deployment
- API and Mistral Studio
- Privacy
- Not established
- Licence
- Open weights under CC BY-NC 4.0
Capability
Modality
Access
Deployment
Pricing
Target user
Evidence
6 claims- Voxtral TTS supports speech generation in English, French, German, Spanish, Dutch, Portuguese, Italian, Hindi, and Arabic. [1]
It supports state-of-the-art performance in 9 languages: English, French, German, Spanish, Dutch, Portuguese, Italian, Hindi, and Arabic.
Mistral. Quoted text is outside CC BY 4.0 and keeps its original rights. - The model can adapt to a custom voice using a reference as little as 3 seconds. [1]
The model was trained to adapt to a custom voice with a reference as little as 3s and capture not just the voice but also nuances like subtle accent, inflections, intonations and even disfluencies similar to those expressed in the reference.
Mistral. Quoted text is outside CC BY 4.0 and keeps its original rights. - The model natively generates up to two minutes of audio, while the API handles arbitrarily long generations. [1]
The model natively generates up to two minutes of audio, and our API handles arbitrarily long generations with smart interleaving.
Mistral. Quoted text is outside CC BY 4.0 and keeps its original rights. - Voxtral TTS is available now via API and can be tested in Mistral Studio and Le Chat. [1]
Available via API and Mistral Studio, it offers cost-effective, high-quality voice generation starting at $0.016 per 1k characters.
Mistral. Quoted text is outside CC BY 4.0 and keeps its original rights. - API pricing starts at $0.016 per 1k characters. [1]
Available via API and Mistral Studio, it offers cost-effective, high-quality voice generation starting at $0.016 per 1k characters.
Mistral. Quoted text is outside CC BY 4.0 and keeps its original rights. - A model with several reference voices is available as open weights on Hugging Face under CC BY-NC 4.0. [1]
A model with several reference voices is available as open weights on Hugging Face under CC BY NC 4.0 license.
Mistral. Quoted text is outside CC BY 4.0 and keeps its original rights.
Sources
1
1
Verified
Versions
1| Version | Effective | Change | Changed fields | State |
|---|---|---|---|---|
| 1 | 2026-10-12 16:06 UTC | publication | None | Current |
In briefs
1- Muse Wonder is aimed at document work, workflows, and coding Daily brief 2026-10-12
Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.