# 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.

- API names: `voxtral-mini-transcribe-realtime-3-0`, `voxtral-mini-transcribe-realtime-3`, `voxtral-mini-transcribe-realtime-latest`
- Status: Public Preview
- Type: Premier, Specialist
- Release date: 2026-10-20
- Version: 3.0
- Context length: --
- Input: audio
- Output: text
- Features: transcriptions
- Speed rating: 4.5/5
- Performance rating: 4/5
- Pricing: Input $0.008 /Min