Voxtral Transcribe 2 by Mistral – Real-time speech-to-text with speaker diarization

Summary: Voxtral Transcribe 2 provides real-time, accurate speech-to-text transcription with speaker diarization, supporting 13 languages and word-level timestamps. It is optimized for live applications, voice agents, and meetings with sub-200ms latency and privacy-focused deployment.

What it does

It transcribes speech in real time while identifying individual speakers, offering multilingual support and detailed timestamps for each word.

Who it's for

Designed for developers and organizations building live apps, voice agents, and meeting transcription tools.

Why it matters

It enables fast, accurate, and privacy-conscious transcription to improve communication and data processing in real-time scenarios.