Skip to content
Live
The Decoder· Matthias Bastian·· 25 days ago72

Mistral AI launches Voxtral 3, a full voice agent stack that listens, thinks, and talks in real time

Mistral AI launches Voxtral 3, a full voice agent stack that listens, thinks, and talks in real time

Brief overview

Mistral AI has released the real-time voice intelligence stack Voxtral 3, including a speech-to-text model (Voxtral Small Transcribe 3), a text-to-speech model (Voxtral Mini TTS 3), and a voice intelligence SDK based on LiveKit.

Same story2 other outlets also reported this

How the accounts differ:The Decoder mentions a text-to-speech model (Voxtral Mini TTS 3) that is not detailed in the first report.

  1. Mistral AI··First

    Mistral AI has launched the Voxtral 3 voice agent SDK and cutting-edge voice models.

  2. The Decoder··+5 h 18 min·Reading now

    Mistral AI has released the real-time voice intelligence stack Voxtral 3.

    Adds:Mentions LiveKit as the base for the voice agent SDK.

  3. MarkTechPost··+18 h 3 min

    Mistral AI releases Voxtral 3: an SDK for speech-to-text, text-to-speech, and voice intelligence agents

    Adds:Specifies 3 transcription models and 1 text-to-speech model in the Voxtral 3 family.

In order of publication · later reports are added as they appear · Compared by AI from each outlet’s title and summary

Article

Mistral AI has launched Voxtral 3, a new family of language models built for real-time voice agents. The system includes a speech-to-text model (Voxtral Small Transcribe 3), a text-to-speech model (Voxtral Mini TTS 3), and a voice agent SDK based on LiveKit. Together, they combine listening, thinking, tool use, and speaking into a single streaming pipeline. Transcription covers more than 50 languages. Text-to-speech output supports over 35 languages and 50 dialects with emotional adaptation. Agents can tap into external systems during live conversations, for example, to book appointments or check invoices.

Mistral says the system can run on your own infrastructure or through EU-hosted APIs to keep data under your control. Pricing starts at $0.0035 per minute for transcription. More details are in the documentation.

AI News Without the Hype – Curated by Humans

Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.

Source: The Decoder · the-decoder.com