Mistral AI releases Voxtral 3 speech models and a voice agent SDK

What happened

Mistral AI released Voxtral 3, a family of transcription and speech generation models, alongside a voice agent SDK built on LiveKit. Transcription supports 50+ languages, while speech generation supports 35+ languages and 50+ dialects; the SDK combines listening, reasoning, tool calling, and speaking in a streaming pipeline that Mistral says completes turns in under one second. The models are available through Mistral’s API, with on-premises or private-cloud deployment available by contacting its team.

Reported by 3 sources

The story so far

Mistral AI released Voxtral 3 transcription and speech generation models, a LiveKit-based voice agent SDK and a voice agents API, 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. Artificial Analysis ranked Voxtral Small Transcribe 3 third on its Speech to Text leaderboard with a 2.1% AA-WER Index. It reported final-transcript AA-WER of 3.3% at 960 ms and 3.6% at 480 ms for Mini Transcribe Realtime 3, 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

Trending now

1. 1DeepSeek Open-Sources DeepInfer and Companion Components, With Model and Hardware Limits
2. 3Perplexity Adds Fully Local Mac Operation to Computer
3. 4OpenAI Introduces Coding Evaluations and Reports Gains in Low-Resource Programming Languages
4. 5NVIDIA Releases Nemotron 3.5 Super VL and Bolt Models for Enterprise and Local Agents