Mistral's Voxtral 3 adds a LiveKit-based voice agent SDK and new speech models in 50+ languages

Released Oct 20, the SDK chains Voxtral Mini Transcribe Realtime 3, a reasoning model like Mistral Small with tool calling, and Voxtral TTS 3 into one streaming pipeline that Mistral says finishes each turn in under a second, over SIP or WebRTC. Transcription starts at $0.0035/min via the API or self-deployment, and Voxtral 2 callers have a migration guide since emotion moves from preset voices to inline tags.