Voxtral Mini Transcribe Realtime 3

Voxtral Realtime Transcribe 3 is a realtime transcription model built for agentic use-cases. It achieves state-of-the-art streaming transcription with configurable latency (80 ms to 2,400 ms), built-in end-of-turn detection, context biasing, and speaker diarization, all in a single streaming session over WebSocket.