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

- Company: The Decoder (the-decoder.com)
- Announced: 2026-10-20T17:17:55+00:00
- Category: new-model
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://the-decoder.com/mistral-ai-launches-voxtral-3-a-full-voice-agent-stack-that-listens-thinks-and-talks-in-real-time/
- Record: https://forck.live/items/25331-mistral-ai-launches-voxtral-3-a-full-voice-agent-stack-that-listens-thinks-and
- Subject: Reporting
- Models affected: Voxtral 3, Voxtral Small Transcribe 3, Voxtral Mini TTS 3
- Pricing: $0.0035 per minute for transcription

Mistral AI has launched Voxtral 3, a family of language models built for real-time voice agents, pairing a speech-to-text model, a text-to-speech model and a LiveKit-based agent SDK. The three parts combine listening, thinking, tool use and speaking into a single streaming pipeline, so agents can reach external systems mid-conversation to book appointments or check invoices. Transcription covers more than 50 languages, while text-to-speech output supports over 35 languages and 50 dialects with emotional adaptation. Mistral says the system can run on a customer's own infrastructure or through EU-hosted APIs to keep data under their control. Pricing starts at $0.0035 per minute for transcription, with more details in the documentation.

## Evidence

Verbatim from https://the-decoder.com/mistral-ai-launches-voxtral-3-a-full-voice-agent-stack-that-listens-thinks-and-talks-in-real-time/:

> 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.

---

Record: https://forck.live/items/25331-mistral-ai-launches-voxtral-3-a-full-voice-agent-stack-that-listens-thinks-and
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md