Voxtral STT 3 - Transcription demo

Voxtral Small Transcribe 3 is state-of-the-art in multilingual transcription, identifying who said what (diarization), and using keyphrases to improve its accuracy (context-biasing). It detects when someone has finished speaking so agents can respond without delay (end-of-turn detection). State-of-the-art speech models and a new developer kit to build voice agents that listen, reason, speak and act in real time. Transcription across 50+ languages, expressive speech across 35+ languages and 50+ dialects. Voxtral 3 is available today, through our EU-hosted API or on your own infrastructure. Learn more: mistral.ai/news/voxtral-3