Introducing Voxtral 3.
Introducing Voxtral 3.
State-of-the-art speech models and a new developer kit to build voice agents that listen, reason, speak and act in real time. Transcription across 50+ languages, expressive speech across 35+ languages and 50+ dialects.
Available today, through our EU-hosted API or on your own infrastructure.
Learn more on the blog → https://mistral.ai/news/voxtral-3