As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/voxtral-transcribe-2/

# Voxtral Transcribe 2 (Mini Transcribe V2 + Voxtral Realtime)

Mistral AI, Voxtral family. Status: current. Type: speech and audio. Released: 2026-02-04.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Mistral API (batch) | `voxtral-mini-2602` | https://api.mistral.ai/v1/audio/transcriptions | https://docs.mistral.ai/models/model-cards/voxtral-mini-transcribe-26-02 |
| Mistral API (realtime) | `voxtral-mini-transcribe-realtime-2602` |  | https://docs.mistral.ai/models/model-cards/voxtral-mini-transcribe-realtime-26-02 |
| Hugging Face (Realtime, open weights) | `mistralai/Voxtral-Mini-4B-Realtime-2602` |  | https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-2602 |
| Web app |  |  | https://chat.mistral.ai |

## Pricing

- Per minute, batch: $0.003
- Per minute, realtime: $0.006
- Unit as published: USD per minute of audio (voxtral-mini-2602 batch / voxtral-mini-transcribe-realtime-2602)
- Source: https://mistral.ai/news/voxtral-transcribe-2
- Last checked: 2026-09-29

## Specs

- Input: audio
- Output: text
- Context window: not published
- Max output: not published
- Open weights: yes
- Licence: apache-2.0

## Where it stands

- Newer speech and audio models in the registry since its release: 67. The 5 newest:
  - NVIDIA Nemotron 3.5 Transcribe (30B-A4B) (2026-10-28) https://postcutoff.com/m/nemotron-3-5-transcribe/
  - Hy-SimulMT-30B-A3B (2026-10-22) https://postcutoff.com/m/hy-simulmt-30b-a3b/
  - Eleven Realtime v1 Max / Mini (2026-10-20) https://postcutoff.com/m/eleven-realtime-v1-max/
  - Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3) (2026-10-20) https://postcutoff.com/m/voxtral-mini-transcribe-3/
  - Voxtral Small Transcribe 3 (2026-10-20) https://postcutoff.com/m/voxtral-small-transcribe-3/
- After it from Mistral AI: Voxtral TTS (2026-03-23) https://postcutoff.com/m/voxtral-tts/
- Weights are public under a permissive licence (Apache-2.0).

## What stands out

- Open-weight realtime ASR under 200 ms: Voxtral Realtime (4B, Apache 2.0) reaches sub-200 ms latency; at 480 ms delay Mistral reports 1-2% WER. Source: https://mistral.ai/news/voxtral-transcribe-2
- Cheap batch transcription with diarization: Mini Transcribe V2: ~4% WER on FLEURS at $0.003/min with speaker diarization, word timestamps, context biasing (up to 100 terms) and audio up to 3 hours. Source: https://mistral.ai/news/voxtral-transcribe-2

## Notes

13 languages (en, zh, hi, es, ar, fr, pt, ru, de, ja, ko, it, nl). Batch model is API-only ('Premier' license); Realtime has open weights. Replaced voxtral-mini-2507 / Voxtral Mini Transcribe (deprecated 2026-02-27, retired 2026-05-31). Tech report arXiv 2602.11298. Accuracy claims are Mistral's. Succeeded by Voxtral Transcribe 3 (2026-10-20): see voxtral-mini-transcribe-3 and voxtral-small-transcribe-3.

```bash
curl https://api.mistral.ai/v1/audio/transcriptions -H "Authorization: Bearer $MISTRAL_API_KEY" \
  -F model=voxtral-mini-2602 -F file=@audio.mp3
```

Sources: https://mistral.ai/news/voxtral-transcribe-2 · https://docs.mistral.ai/models/overview

Model page: https://postcutoff.com/m/voxtral-transcribe-2/