Skip to content
Back

Mistral AINew model

We released the Voxtral 3 audio family, our next generation of speech-to-text and text-to-speech models

AI summary

Written by AI from the official notes. Check them for exact details.

Mistral AI released the Voxtral 3 audio family, featuring new speech-to-text and text-to-speech models in Public Preview.

  • Voxtral TTS 3 offers zero-shot voice cloning and streaming.
  • Voxtral Mini Transcribe 3 provides offline transcription with timestamps.
  • Voxtral Mini Transcribe Realtime 3 enables real-time transcription.
  • Voxtral Small Transcribe 3 also supports offline transcription with timestamps.

Why it matters: Users needing advanced speech-to-text and text-to-speech capabilities should explore these new models.

Official notes on docs.mistral.aiVoxtral 3 announcement

Full release notes5 changes

  • We released the Voxtral 3 audio family, our next generation of speech-to-text and text-to-speech models. All four models are in Public Preview. See the Voxtral 3 announcement and the audio models pricing.
  • Voxtral TTS 3 (voxtral-mini-tts-3-0): text-to-speech with zero-shot voice cloning, streaming, and contextual delivery. See the model card.
  • Voxtral Mini Transcribe 3 (voxtral-mini-transcribe-3-0): offline transcription and diarization with timestamps. See the model card.
  • Voxtral Mini Transcribe Realtime 3 (voxtral-mini-transcribe-realtime-3-0): real-time transcription. See the model card.
  • Voxtral Small Transcribe 3 (voxtral-small-transcribe-3-0): offline transcription and diarization with timestamps. See the model card.