Mistral AI Unveils Voxtral TTS — New Multilingual Speech Synthesis Model
Mistral AI has released Voxtral TTS, a speech synthesis model with 4 billion parameters that supports 9 languages, emotionally expressive speech, low latency, and easy voice adaptation. The model is available via API and Mistral Studio, starting at $0.016 per 1,000 characters.
Mistral
ElevenLabs





