Post-Cutoff
Search For AI agents

Mistral AIVoxtral familyCurrentSpeech and audioReleased 4 Feb 2026

Voxtral Transcribe 2 (Mini Transcribe V2 + Voxtral Realtime)

Model idvoxtral-mini-2602

Price$0.003 per minute, batch

Checked29 September 2026

Where it stands

67newer speech and audio models since its release

The 5 newest are listed. All speech and audio models

After it from Mistral AI
Voxtral TTS23 Mar 2026
Weights
Weights are public under a permissive licence (Apache-2.0).

How to call it

4 ways to use Voxtral Transcribe 2 (Mini Transcribe V2 + Voxtral Realtime), with the model id each provider expects.

Providers, model ids, endpoints and docs for Voxtral Transcribe 2 (Mini Transcribe V2 + Voxtral Realtime)
ProviderModel idEndpointDocs
Mistral API (batch) voxtral-mini-2602 https://api.mistral.ai/v1/audio/transcriptions docs.mistral.ai
Mistral API (realtime) voxtral-mini-transcribe-realtime-2602 docs.mistral.ai
Hugging Face (Realtime, open weights) mistralai/Voxtral-Mini-4B-Realtime-2602 huggingface.co
Web app chat.mistral.ai

Pricing

Prices for Voxtral Transcribe 2 (Mini Transcribe V2 + Voxtral Realtime)
Per minute, batch$0.003
Per minute, realtime$0.006

As published: “USD per minute of audio (voxtral-mini-2602 batch / voxtral-mini-transcribe-realtime-2602)”.

Source: mistral.ai, checked 29 September 2026.

Specs

Input
Audio
Output
Text
Context window
Not published
Max output
Not published
Open weights
Yes
Licence
Apache-2.0
Released
4 February 2026
Status
Current
Type
Speech and audio

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • 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: mistral.ai

  • 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: mistral.ai

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.

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