Skip to content
Original
ProductsArthur Mensch · XFrom the source· @arthurmensch·· 2 hours agoPicks

2.5K views · 71 likes · 7 reposts (at collection)

Voxtral 3 introduces Transcribe and Speech models for Mistral’s voice agents API

Who
Arthur Mensch
What
highlighted Voxtral's on-the-fly diarization and end-of-turn detection

What happened

Mistral AI introduces Voxtral 3, describing its Transcribe and Speech models as state-of-the-art and powering its new voice agents API. Arthur Mensch adds that Voxtral diarizes and detects end-of-turn on the fly, running on your infrastructure or Mistral’s infrastructure, including the one in the train station. https://twitter.com/MistralAI/status/2112574615318876178

Why it matters

The deployment options give teams a concrete infrastructure choice when considering Voxtral for voice workflows that require speaker diarization and end-of-turn detection during processing.

The story so far

Mistral AI released Voxtral 3 transcription and speech generation models, a voice agents API and a LiveKit-based voice agent SDK, with the models available through its EU-hosted API or for deployment on customers’ infrastructure. Organizations seeking to run the full stack on-premises or in a private cloud must contact Mistral’s team. Transcription supports more than 50 languages, while speech generation supports more than 35 languages and more than 50 dialects. The SDK combines listening, reasoning, tool calling and speaking in a streaming pipeline that Mistral says completes conversational turns in under one second. Arthur Mensch said Voxtral also identifies speakers and detects when a speaker’s turn ends as audio arrives. The Decoder reported that transcription pricing starts at $0.0035 per minute. Artificial Analysis ranked Voxtral Small Transcribe 3 third on its Speech to Text leaderboard with a 2.1% AA-WER Index. It measured Mini Transcribe Realtime 3’s final-transcript AA-WER at 3.3% at 960 ms and 3.6% at 480 ms, compared with its predecessor’s 5.2%. Artificial Analysis also ranked Voxtral 3 TTS 12th in both its Provider Voice and Controlled Voice arenas and reported a price of $13 per million characters.

Keep reading

Latest daily · Issue 27TorchNeuron brings native PyTorch support for Hugging Face models on AWS Trainium

Trending now

  1. 2DeepSeek Open-Sources DeepInfer and API Components, With Model and Hardware Limits
  2. 3OpenAI Acquires Orchestra Bio to Expand AI Tools for Drug Development
  3. 4Google Rolls Out Gemini Personal Intelligence to Android Auto, With Google Built-In Cars to Follow
  4. 5OpenAI Rolls Out Locked Chats in ChatGPT With PIN and Biometric Access

Tomorrow at 08:00, a briefing like this arrives in your inbox.

The same kind of briefing as the one above: a few stories worth reading. Free. Mail starts after you confirm, and every letter has a one-click unsubscribe. Read a past issue · 2026-10-20