From the source
Mistral has introduced Voxtral 3, a family of speech-to-text and text-to-speech models paired with a voice agent SDK that combines listening, reasoning, tool calling and speaking in one real-time streaming pipeline.
- The company says building voice agents that can listen, reason, act and speak reliably at the same time has remained difficult, and Voxtral 3 is meant for contact-center agents, service desks, virtual assistants and hands-free copilots.
- The speech-to-text model, Voxtral Small Transcribe 3, is state-of-the-art in multilingual transcription and covers more than 50 languages, including 24 official EU languages, with diarization, context biasing and end-of-turn detection.
- Mistral says it outperforms Whisper, Scribe v2 and Gemini 3.5 Transcribe, while the 4B-parameter Mini variant transcribes at $0.0035 per minute.
- Voxtral Mini TTS 3 handles speech synthesis in more than 35 languages and 50 dialects, with voices that adjust emotion, pace and emphasis to the conversation.
- Pro Voice adaptation can reproduce a speaker's character and speaking style across languages from 30 minutes of audio.
- Voxtral 3 is available today through Mistral's EU-hosted API or for self-deployment, so organizations control where audio is processed and whether conversations are retained.
