Voxtral transcribes at the speed of sound.
This title could be clearer and more informative.Try out Clickbait Shieldfor free (5 uses left this month).
Mistral AI released Voxtral Transcribe 2, featuring two speech-to-text models: Voxtral Mini Transcribe V2 for batch processing and Voxtral Realtime for live applications with sub-200ms latency. Both models support 13 languages, speaker diarization, and word-level timestamps. Voxtral Realtime is open-source under Apache 2.0
Table of contents
Highlights.Voxtral Realtime.Voxtral Mini Transcribe V2.Audio playground.Transforming voice applications.Get started.We’re hiring.Sort: