Mistral Releases Voxtral Transcribe 2 Models

Mistral recently released Voxtral Transcribe 2, a family of two speech-to-text models including the open-weights Voxtral-Mini-4B-Realtime-2602 (Apache-2.0, 8.87GB on Hugging Face) and a closed-weight voxtral-mini-latest accessible via the Mistral API. The company updated its API console with a speech-to-text playground offering diarization and downloads in text, SRT, and JSON; the release follows the original Voxtral from July 2025.
Key Points
- 1Announces two Voxtral Transcribe 2 models, including open-weight Voxtral-Mini-4B-Realtime-2602 (8.87GB) on Hugging Face
- 2Provides API-accessible closed-weight model and integrated playground for diarized speech-to-text testing and downloads
- 3Enables practitioners to run real-time transcription locally or via Mistral API with diarization outputs
Scoring Rationale
Strong practical release with open weights and API integration, moderate novelty limited to incremental ASR improvements.
Sources
Public references used for this report.
Practice interview problems based on real data
1,625 SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems

