🔊Introducing Voxtral TTS: our new frontier open-weight model for...
Mistral AI@MistralAI
13 views
Mar 26, 2026
~1 min read
Advertisement
1
🔊Introducing Voxtral TTS: our new frontier open-weight model for natural, expressive, and ultra-fast text-to-speech
🎭Realistic, emotionally expressive speech.
🌍Supports 9 languages and accurately captures diverse dialects.
⚡Very low latency for time-to-first-audio.
🔄Easily adaptable to new voices
🎭Realistic, emotionally expressive speech.
🌍Supports 9 languages and accurately captures diverse dialects.
⚡Very low latency for time-to-first-audio.
🔄Easily adaptable to new voices
2
Voxtral TTS is built for global applications supporting 9 languages and powering voice workflows.
✅ Full audio intelligence: Works with Voxtral Transcribe for end-to-end speech-to-speech, or plugs into any STT + LLM stack.
✅ Built for business: From customer support to real-time translation, it’s the output layer that passes the human test.
🎥 See it in action:
✅ Full audio intelligence: Works with Voxtral Transcribe for end-to-end speech-to-speech, or plugs into any STT + LLM stack.
✅ Built for business: From customer support to real-time translation, it’s the output layer that passes the human test.
🎥 See it in action:
3
State-of-the-art performance.
In zero-shot custom voice tests, Voxtral TTS outperformed ElevenLabs v2.5 Flash - judged by native speakers for naturalness, accent accuracy, and similarity to the original voice.
In zero-shot custom voice tests, Voxtral TTS outperformed ElevenLabs v2.5 Flash - judged by native speakers for naturalness, accent accuracy, and similarity to the original voice.
4
Experiment with Voxtral TTS directly in the Mistral Studio playground. Select one of the Mistral voices or record your own.
5
Check out our blog post for details: mistral.ai/news/voxtral-t…
