mistralai

Mistral: Voxtral Small Transcribe 3

mistralai/voxtral-small-transcribe-3-0

Our take

AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.

OpenRouter’s catalog describes mistralai/voxtral-small-transcribe-3-0 as Mistral’s flagship speech-to-text model for converting audio into transcripts. The listing reports timestamped output, speaker diarization, and context biasing for domain-specific vocabulary. These are source-reported capabilities rather than independently measured results. The source pack does not include an independent model card, benchmark findings, or language-support details, so prospective users should validate accuracy, latency, and diarization quality on representative audio before adoption.[1]

Strengths

OpenRouter lists audio input and transcription output for this exact variant.[1]
The catalog reports transcripts with timestamps and speaker diarization.[1]
It reports context biasing for domain-specific vocabulary.[1]

Limitations

Evidence comes only from OpenRouter's catalog; no independent model card was available in this source pack.[1]
No measured accuracy, latency, language coverage, or diarization-quality results are supplied.[1]
Real-world suitability should be validated on representative workloads before deployment.[1]

Where to use it

A reasonable fit to evaluate for transcription pipelines that need speaker labels.[1]
Worth testing where timestamps are needed for editing, indexing, or review.[1]
Potentially useful for domain-specific speech after testing whether context biasing improves recognition.[1]

Sources

[1] OpenRouter catalog · Mistral: Voxtral Small Transcribe 3Sources checked: Nov 13, 2026

About this model

Description below is the original text supplied by OpenRouter, shown in the source language.

Voxtral Small Transcribe 3 is Mistral's flagship speech-to-text model. It takes audio input and returns a transcript with timestamps and speaker diarization, and supports context biasing for domain-specific vocabulary. Suited...

Specifications

Model ID: mistralai/voxtral-small-transcribe-3-0
Canonical ID: mistralai/voxtral-small-transcribe-3-0-20261020
Creator: mistralai
Added to OpenRouter: 20.10.2026
Context length: 65,536
Modality: audio->transcription
Input modalities: audio
Output modalities: transcription
Token pricing: No per-token price in the source snapshot — see OpenRouter for the billing unit
Knowledge cutoff: —
Expiration date: —

Tasks and capabilities

A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.

Task	Grade	Source-declared capability
General quality	No measurement	—
Coding	No measurement	—
Agents	No measurement	—
Writing	No measurement	—
Reasoning	No measurement	—
Document analysis	No measurement	—
Vision	No measurement	—
Image generation	No measurement	—
Audio	No measurement	input: audio
Video	No measurement	—
Embeddings	No measurement	—

Evaluations

No evaluations are supplied for this model.

How grades work

Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.

S — S — top 10% of the cohort
A — A — next 20% of the cohort
B — B — next 30% of the cohort
C — C — below the B band

Providers

Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.

Provider	Context length	Price in /1M	Price out /1M	Latency p50 (30m, s)	Throughput p50 (30m, tok/s)	Uptime (30m)
Mistral	65,536	—	—	—	—	100%
Mistral	0	—	—	—	—	—
Mistral	0	—	—	—	—	100%

Provider data retrieved: 13.11.2026

No published articles identify this model yet.