# TestingCatalog — Mistral launches Voxtral 3 with a voice agent SDK

- Company: TestingCatalog (testingcatalog.com)
- Announced: 2026-10-21T06:12:44+00:00
- Category: new-model
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://www.testingcatalog.com/mistral-launches-voxtral-3-with-a-voice-agent-sdk/
- Record: https://forck.live/items/25688-mistral-launches-voxtral-3-with-a-voice-agent-sdk
- Subject: AI models / agents / unreleased features
- Models affected: Voxtral 3, Voxtral Small Transcribe 3, Voxtral Mini Transcribe 3, Voxtral Mini TTS 3.0, Mistral Small
- Pricing: Voxtral Mini Transcribe 3: $0.0035 per minute for batch use, $0.008 per minute for the realtime version; Voxtral Mini TTS 3.0: $13 per million characters

Mistral has launched Voxtral 3, a family of speech-to-text and text-to-speech models plus a voice agent SDK that combines listening, reasoning, tool calling, and speaking in one real-time streaming pipeline. The stack is built for contact centers, service desks, virtual assistants, and hands-free copilots, and is available now through Mistral's EU, US, and global API endpoints. Companies can also deploy it in a private cloud or on their own infrastructure. Voxtral Small Transcribe 3 covers more than 50 languages with diarization, context biasing, and end-of-turn detection, and in Mistral's 45-language FLEURS chart it records forced and inferred error rates of 4.1% and 4.0%. The 4-billion-parameter Voxtral Mini Transcribe 3 costs $0.0035 per minute for batch use, while the realtime version costs $0.008 per minute and runs at sub-500 millisecond latency. Voxtral Mini TTS 3.0 delivers batch and realtime speech in more than 35 languages and over 50 dialects for $13 per million characters, and supports prompt instructions, contextual TTS, a vocabulary library, and voice cloning from more than 30 minutes of audio. The LiveKit-based SDK runs transcription, reasoning, tool use, and speech generation concurrently, keeping turns under one second and stopping the agent when a caller cuts in.

## Evidence

Verbatim from https://www.testingcatalog.com/mistral-launches-voxtral-3-with-a-voice-agent-sdk/:

> The LiveKit-based SDK runs transcription, reasoning, tool use, and speech generation concurrently. A general model such as Mistral Small can reason and call tools while the voice models process the conversation, keeping turns under one second and stopping the agent when a caller cuts in.

---

Record: https://forck.live/items/25688-mistral-launches-voxtral-3-with-a-voice-agent-sdk
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md