Home/Voice and audio/Voxtral 3
Voxtral 3
Mistral speech models for transcription and speech, plus a voice agent SDK that runs the pipeline in real time.
Mistral says Voxtral 3 adds speech-to-text and text-to-speech models and a voice agent SDK built on LiveKit. Listening, reasoning, tool calls, and speech run as one real-time pipeline. Transcription is listed for 50+ languages and text to speech for 35+ languages. It is available through Mistral's API or self-deployment.
Where it ranks
07 in Voice and audio
Transcription, speech, and a voice agent pipeline from Mistral.
See the voice and audio list
Pricing
Check site
Mistral says it is available through the API or self-deployment. Check Mistral for API pricing.
Checked
Added October 22, 2026
Last verified October 30, 2026
Dated releases
Mistral released Voxtral 3: speech-to-text, text-to-speech, and a real-time voice agent SDK.
Also in voice and audio
- ElevenLabs · Text to speech, voice tools, and an API for putting speech in a product.
- Suno · Makes a full song, vocals included, from a description or your lyrics.
- Descript · Edit video and podcasts by editing the transcript text.