Voice-agent builders wanting their own voice stack in nine languages; the open weights are non-commercial, so paid use goes through Mistral's API.
Kenning's take
What it does
Voxtral TTS is a 4-billion-parameter text-to-speech model from Mistral AI that produces expressive speech in 9 languages. It can adapt to a new voice from a short recording, and Mistral says listeners preferred it to ElevenLabs Flash v2.5 for naturalness. It is available through Mistral's API, Mistral Studio and Le Chat, with a version open-weighted for non-commercial use.
- Expressive speech in 9 languages
- Voice adaptation from a recorded sample
- Low time-to-first-audio for voice agents
- Built-in Mistral voices in American, British and French dialects
- Open weights under CC BY-NC 4.0
Who it suits. Developers and companies building voice agents or narrated content who want their own voice stack.
Key facts
- Category
- AI models
- Part of
- Le Chat (Vibe by Mistral)
- Made by
- Mistral AI
- Released
- 23 March 2026
- How to get it
- Mistral API, Mistral Studio and Le Chat; open weights on Hugging Face for non-commercial use
- Works on
- API, Web, open-weights
- In the UK
- Yes
- Free plan
- open weights under CC BY-NC 4.0
- API price
- $0.016 per 1,000 characters
FAQ
When was Voxtral TTS released?
Mistral AI released Voxtral TTS on 23 March 2026.
How much does Voxtral TTS cost?
$0.016 per 1,000 characters on Mistral's API.
Can Voxtral TTS clone a voice?
Yes, Mistral says it adapts to new voices, and Mistral Studio lets users record their own voice.
Facts from the maker's own pages and the sources listed. Checked 2026-10-11.
Similar tools
Devstral 2
Mistral's open-weight coding model family, now retired from the API in favour of Mistral Medium 3.5
Mistral 3
Mistral's December 2025 family of open models, from the small Ministral 3 sizes up to Mistral Large 3
Mistral Small 4
An open Mistral model that handles chat, reasoning, coding and images in one 119B mixture-of-experts model
Mistral OCR 3
Mistral's December 2025 document reading model that pulls text, tables and images out of PDFs and scans