Simon Willison • 2/4/2026

Voxtral transcribes at the speed of sound

Read Original

Mistral has launched Voxtral Transcribe 2, a new family of Whisper-like models for audio transcription. It includes an open-weights real-time model (Voxtral-Mini-4B-Realtime) available on Hugging Face and a closed model via the Mistral API priced at $0.003/min. The article details the models' capabilities, provides a demo link, and shows example API usage.

0 comments
#transcription #Hugging Face #AI Models
Voxtral transcribes at the speed of sound

Comments

No comments yet

Be the first to share your thoughts!

Browser Extension

Get instant access to AllDevBlogs from your browser

Top of the Week

1
Quoting Thariq Shihipar
Simon Willison • 2 votes
2
Using Browser Apis In React Practical Guide
Jivbcoop • 2 votes
3
Top picks — 2026 January
Paweł Grzybek • 1 votes
4
In Praise of –dry-run
Henrik Warne • 1 votes
5
Deep Learning is Powerful Because It Makes Hard Things Easy - Reflections 10 Years On
Ferenc Huszár • 1 votes
6
Vibe coding your first iOS app
William Denniss • 1 votes
7
AGI, ASI, A*I – Do we have all we need to get there?
John D. Cook • 1 votes
8
Dew Drop – January 15, 2026 (#4583)
Alvin Ashcraft • 1 votes