Voxtral 3

Latest news

1. 20 Oct
   Voxtral 3: voice agent SDK plus speech models for real-time conversations

   Voxtral 3 is a new family of speech-to-text and text-to-speech models paired with a voice agent SDK for real-time, multi-step conversational workflows. It supports 50+ languages, emotional speech synthesis, deep tool integration, and can be used via Mistral’s EU-hosted API or self-deployed.

   Models · 1 source

   

Articles

No articles about Voxtral 3 yet.