whatmodel.sh / stt / Voxtral Mini Transcribe Realtime 3
Voxtral Mini Transcribe Realtime 3
↗ share
+ contribute
Voxtral Mini Transcribe Realtime 3 is a closed-weights speech-to-text model from Mistral AI, released October 2026. Licence: proprietary.
Catalogue identity notes
20 October Voxtral 3 family release; exact batch/realtime/TTS variant retained. Public API confirmed, public downloadable weights not verified. No incompatible FLEURS subset or third-party AA result imported.
Model information sources
$ how it compares
Scored speech-to-text models released closest to Voxtral Mini Transcribe Realtime 3, out of 178 with a score.
| # | model | score | where |
|---|---|---|---|
| 1 |  Muse Voice Transcribe 1.0 | 71±3 | api $0.0030/audio min |
| 2 |  Grok Voice Transcribe 2.0 | 70±3 | api $0.0017/audio min |
| 4 |  Universal-3.6 Pro Realtime | 70±3 | api $0.0075/audio min |
| 5 |  Linden 1 (Agent STT) | 69±3 | api $0.0050/audio min |
| 24 |  Qwen-Audio-3.0-ASR | 62±4 | comparison only |
see all speech-to-text models · find the ones that fit your machine
$ where to run it
Through an API
api · $0.0080/audio min · mistral.ai ↗ · price sourceOfficial USD API rate for this Voxtral 3 variant, observed 2026-10-21. Enterprise self-deployment terms separate.
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json