Mistral releases Voxtral 3 speech models and voice agent SDK
Original title: Voxtral 3
The family adds multilingual transcription and speech synthesis, offered on an EU-hosted API or for self-hosting.
Mistral introduced Voxtral 3, a family of speech-to-text and text-to-speech models plus a voice agent SDK that streams listening, reasoning, tool calling, and speech. Voxtral Small Transcribe 3 and the 4-billion-parameter Mini variant cover more than 50 languages, with diarization, context biasing, and end-of-turn detection. Voxtral Mini TTS 3 covers 35+ languages and 50+ dialects, and Pro Voice adaptation is described as using 30 minutes of audio. Deployment is through Mistral’s EU-hosted API or on a customer’s own infrastructure.
Unconfirmed: Accuracy, diarization, and comparison figures are Mistral’s own benchmark claims.
- Mistral prices Voxtral Mini Transcribe 3 at $0.0035 per minute.
- Transcription support is listed at 50+ languages, including 24 official EU languages.
- Mistral says Small beats Whisper, Scribe v2, and Gemini 3.5 Transcribe on a 45-language FLEURS set.
- Pro Voice adaptation is described as needing 30 minutes of source audio.
- Vendors
- Mistral
- Products
- Voxtral 3 voice agent SDK
From the original article
9 min read at mistral.ai
Voxtral 3 introduces a cutting-edge voice agent SDK and state-of-the-art speech models designed for real-time, multi-step conversations across 50+ languages. It combines accurate transcription, natural speech synthesis with emotional adaptability, and deep tool integration for seamless workflow automation.
By ilreb · mistral.ai
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.