Mistral: Voxtral Mini Transcribe 3

Voxtral Mini Transcribe 3 is Mistral's compact speech-to-text model. It takes audio input and returns a transcript with timestamps and speaker diarization. It also supports context biasing for domain…

mistralai/voxtral-mini-transcribe-3-0-20261020

Voxtral Mini Transcribe 3 is Mistral's compact speech-to-text model. It takes audio input and returns a transcript with timestamps and speaker diarization. It also supports context biasing for domain terms. It is small enough to self-deploy in resource-constrained environments, and fits meeting notes, call analytics, and voice-agent pipelines where cost matters.

Specifications & capabilities

Input
audio
Output
transcription
Context window · tokens
65536
Published model ID
voxtral-mini-transcribe-3-0
Capabilities
audioInput, streaming, transcription
Description source ↗

Published prices

1–2 / 2

voxtral-mini-transcribe-3-0 ↗

$0.0035

Inference provider
mistral
Platform
Mistral
Unit
audio_minute
Currency
USD
Billing conditions
Billing label
Per input audio minute

mistralai/voxtral-mini-transcribe-3-0 ↗

$0.0001

Inference provider
openRouter
Platform
OpenRouter
Unit
catalog_quote
Currency
USD
Billing conditions
raw_field
prompt
billing_unit_status
unverified
Billing label
Published scalar; billing unit unverified

Provider specifications & access

1–2 / 2

voxtral-mini-transcribe-3 ↗

source model id
voxtral-mini-transcribe-3
hosting
gateway
platforms
  • Cheaper Inference
architecture
input_modalities
    output_modalities
      capabilities

        Voxtral Mini Transcribe 3 ↗

        source model id
        voxtral-mini-transcribe-3-0
        hosting
        mistral-hosted
        platforms
        • Mistral
        context length
        32000
        architecture
        input_modalities
        • audio
        output_modalities
        • transcription
        capabilities
        • streaming
        • transcription

        Safety assessments

        1–1 / 1

        Foundation Model Transparency Index 2025 ↗

        18 / 100

        source id
        stanfordFMTI
        canonical model id
        mistralai/voxtral-mini-transcribe-3-0-20261020
        taxonomy
        transparency
        hazard category
        transparency
        hazard name
        Organization transparency
        policy area
        Mistral
        assessment type
        organization-level disclosure
        metric
        disclosure_score
        result label
        18 / 100
        sample size
        100
        updated at
        2026-11-09T18:08:05.227Z

        Source specification observations

        1–3 / 3

        mistral ↗

        field
        context_length
        value
        32000
        normalized value
        32000
        scope
        source-model
        source id
        mistral
        confidence
        1

        openRouter ↗

        field
        context_length
        value
        65536
        normalized value
        65536
        scope
        source-model
        source id
        openRouter
        confidence
        1

        openRouter ↗

        field
        max_output_tokens
        value
        52428
        normalized value
        52428
        scope
        source-model
        source id
        openRouter
        confidence
        1

        Original sources

        1–7 / 7

        OpenRouter · Model page ↗

        Mistral AI · Model documentation ↗

        Mistral AI · legal ↗

        api.cheaperinference.com · Source snapshot ↗

        GitHub · Catalog ↗

        Mistral AI · Catalog ↗

        OpenRouter · Catalog ↗

        Source links

        1–4 / 4

        Explore more models

        Models

        Loading
        EVIDENCE / COMPARISON

        Benchmarks

        Explore every benchmark

        Loading

        These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

        Install TensorTrace