$ cat wiki/models/voxtral-small-transcribe-3.md
Voxtral Small Transcribe 3
Spec
| Attribute | Value |
|---|---|
| Developer | Mistral AI |
| Released | 2026-10-20 |
| Announced | 2026-10-20 |
| Context window | unknown |
| Pricing | $0.0040/min |
| License | unknown |
| Availability | Mistral API; contact Mistral for private deployment |
| Specifications follow the launch announcement; context window and license terms are not established by that source. (source) |
Release Date
Announced and available through the API on 2026-10-20. Speech transcription with diarization and context biasing across over 50 languages. (source)
Benchmarks
The vendor claims leading multilingual transcription and diarization. Its FLEURS comparison averages 45 shared languages and uses character error rate for Japanese, Korean, Thai and Chinese, word error rate otherwise. Numerical chart values were not recovered reliably; no independent ranking is asserted. (source)
Use Cases
Transcription involving multiple speakers and domain vocabulary. (source)
Compared To
The Voxtral voice pipeline uses separate transcription, reasoning and speech-generation models. Its reasoning stage can be replaced independently; family-level voice-agent claims are not this model's standalone benchmark. See Agents (LLM Agents). (source)
Sources
- Launch announcement and immutable capture; linked model documentation and model weights were not reviewed.