# Voxtral Small Transcribe 3

mistral, released 2026-10-20

**Verdict: conditional.** Conditional. Voxtral Small Transcribe 3 is Mistral's flagship speech-to-text model, billed per minute on the Mistral API with diarization and context biasing, and Mistral's own FLEURS and diarization charts put it ahead of Whisper large-v3, GPT Transcribe and Scribe v2, tied with Microsoft AI Transcribe 2 on FLEURS. The deciding caveat is that those charts are Mistral's, the model docs label it Public Preview, and no open weights are stated. Suits teams that want regional-endpoint transcription with speaker labels and can validate accuracy on their own audio. Last verified 2026-10-23.

## Pricing

- Input: $0.004 / min of audio
- Output: Billed per minute (single rate)
- Context: Per-minute billing; 32k context per docs

## Strengths

- Meeting, call and interview transcription that needs speaker labels; Mistral lists diarization and a diarization cpWER chart (18.4% for Small vs 18.6% for Mini, Mistral-reported)
- Domain vocabulary such as earnings calls, where context biasing is documented (Mistral reports Earnings 22 keyphrase recall of 81.4% without context and 94.6% with context; Scribe v2 is 84.0% without and 94.3% with context, so Small does not lead without context and leads by only 0.3 points with it)
- Multilingual transcription; the launch post says 50+ languages and Mistral's FLEURS average over the 45-language intersection is 4.1% WER with the language specified, 4.0% auto-detected
- Buyers who want regional endpoints; the post says the API is hosted on European, US and global endpoints, with on-premises or private cloud by talking to Mistral
- Self-hosting from open weights; the pages we read state no open weights, the model is listed as Premier tier, and the launch post routes full on-premises or private cloud deployment through Mistral's team
- Live, low-latency streaming transcription; that is the separate Mini Transcribe Realtime 3 model
- Anything that needs accuracy claims confirmed outside Mistral: every benchmark we read is Mistral's own chart

## Benchmarks

- FLEURS 45-language macro WER, language specified (Mistral-reported): 4.1% (https://mistral.ai/news/voxtral-3/)
- FLEURS 45-language macro WER, language inferred (Mistral-reported): 4.0% (https://mistral.ai/news/voxtral-3/)
- Diarization cpWER (Mistral-reported): 18.4% (https://mistral.ai/news/voxtral-3/)

## Sources

- [Mistral: Voxtral 3](https://mistral.ai/news/voxtral-3/)
- [Mistral news index](https://mistral.ai/news)
- [Mistral docs: Voxtral Small Transcribe 3 model page](https://docs.mistral.ai/models/voxtral-small-transcribe-3-0)
- [Mistral models overview](https://docs.mistral.ai/models/overview)

Canonical: https://neomanex.com/models/voxtral-small-transcribe-3
