Mistral AI releases Voxtral 3 voice agent model stack
What happened
On 21 October 2026, Mistral AI released Voxtral 3, a family of models for real-time voice agents. According to The Decoder, the stack includes the speech-to-text model Voxtral Small Transcribe 3, the text-to-speech model Voxtral Mini TTS 3 and a LiveKit-based voice agent SDK. The report says the setup combines listening, thinking, tool calling and speaking into a single streaming pipeline. Information disclosed so far centres on the model composition and pipeline design, with no further details yet on performance metrics, availability or launch timing.
Written by AI from the reports · updated 3 h ago
Timeline
Follow the reports to see the event from each side.
- The DecoderMistral AI launches Voxtral 3, a full voice agent stack that listens, thinks, and talks in real time
Mistral AI launched Voxtral 3, a new family of language models built for real-time voice agents. The system combines speech-to-text, text-to-speech, and a voice agent SDK, supports more than 50 languages, and lets agents tap into external tools during live conversations. It can run on your own infrastructure or through EU-hosted APIs to keep data under your control.
Heat of this event
Current heat 9·Peak in the comparable range 10（Oct 21 03:00）·Change over 24 hours in the comparable range –
The trend compares only the same accounts observed without a break, so its range can be narrower than the current heat count. Move the pointer or tap the chart to see each hour; with a keyboard, use the left and right arrow keys.