Mistral releases Voxtral 3 speech models and voice agent SDK
Mistral AI has released Voxtral 3, a family of speech-to-text and text-to-speech models plus a voice agent SDK. The company says its transcription model, Voxtral Small Transcribe 3, is state-of-the-art across more than 50 languages, and its text-to-speech model, Voxtral Mini TTS 3, adjusts emotion and pace to the conversation in 35+ languages and 50+ dialects. The SDK combines listening, reasoning, tool calling and speaking in one streaming pipeline, and Mistral says each turn completes in under one second. Voxtral 3 is available through Mistral's API with EU, US and global endpoints, or can be deployed on a company's own infrastructure.