Skip to content

Mistral AI · Transcription

Voxtral Small Transcribe

Mistral AI 🇫🇷TranscriptionOpen weights. One of its sources says the weights are publicly available.

A small audio understanding model released in July 2025

Max context
33K
Listings
4
Providers
3

Evidence and sources

Sources: Mistral API data, LiteLLM data, Models.dev dataPrimary data from Mistral API from LiteLLM: variant from Models.dev: weights availability
Tags from its sources:instructaudio

Advantages and trade-offs

Compared with 10 representative transcription models

Advantages

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.

Input & output

as stated by the model's providers
Text
Audio
Text

Capabilities

Supported operations and provider-stated features

Function callingStructured outputAudio input

Listings

 Mistral AIvoxtral-small-2507Sources: LiteLLM data, Mistral API data, Models.dev data33K$0.10cache read $0.01$0.40
 Cortecs AIvoxtral-small-2507Sources: Cortecs EU Router data, Models.dev data32K

2 listings without a price are hidden.

Benchmarks

No benchmark scores yet.

Around the web

  • Voxtral - arXiv

    Webpage: · https://mistral.ai/news/voxtral/ Model weights: · https://huggingface.co/mistralai/Voxtral-Mini-3B-2507 https://huggingface.co/mistralai/Voxtral-Small-24B-2507 Evals: · https://huggingface…

    arxiv.org

  • Voxtral - a mistralai Collection
    mistralai 's Collections Mistral Medium 3.5 Voxtral Mistral Small 4 Devstral 2 Mistral Large 3 …mistralai 's Collections Mistral Medium 3.5 Voxtral Mistral Small 4 Devstral 2 Mistral Large 3 Ministral 3 Ministral 3 - Additional Checkpoints Speech Evals Voxtral updated Apr 14 Mistral AI Audio mo…

    huggingface.co

  • mistralai (Mistral AI_)
    mistralai/Voxtral-4B-TTS-2603 Text-to-Speech · Updated Mar 31 · 1.63k · 893 mistralai/Voxtral-Mini-4B-Realtime-2602 Automatic Speech Recognition · …mistralai/Voxtral-4B-TTS-2603 Text-to-Speech · Updated Mar 31 · 1.63k · 893 mistralai/Voxtral-Mini-4B-Realtime-2602 Automatic Speech Recognition · 4B · Updated Mar 11 · 2.15M · 943 mistralai/Voxtral-…

    huggingface.co

  • Voxtral - Hugging Face
    Voxtral Voxtral is an upgrade of Ministral 3B and Mistral Small 3B, extending its language …Voxtral Voxtral is an upgrade of Ministral 3B and Mistral Small 3B, extending its language capabilities with audio input support. It is designed to handle tasks such as speech transcription, translat…

    huggingface.co

  • mistralai/Voxtral-Mini-4B-Realtime-2602 at dba55be59b82c62342670cd20fcc66d8c2e569ae
    mistralai / Voxtral-Mini-4B-Realtime-2602 like 942 Follow Mistral AI_ 18.9k Automatic Speech Recognition Safetensors 13 languages …mistralai / Voxtral-Mini-4B-Realtime-2602 like 942 Follow Mistral AI_ 18.9k Automatic Speech Recognition Safetensors 13 languages vllm voxtral_realtime mistral-common Eval Results arxiv: 2602.11298 L…

    huggingface.co

  • mistralai/Voxtral-Mini-4B-Realtime-2602 at b1bd47d9cbe99d2b7104eb4a81b092ca4add2b1c
    mistralai / Voxtral-Mini-4B-Realtime-2602 like 782 Follow Mistral AI_ 16.5k Automatic Speech Recognition Safetensors 13 languages …mistralai / Voxtral-Mini-4B-Realtime-2602 like 782 Follow Mistral AI_ 16.5k Automatic Speech Recognition Safetensors 13 languages vllm voxtral_realtime mistral-common arxiv: 2602.11298 License: apach…

    huggingface.co

  • README.md · mistralai/Voxtral-Small-24B-2507 at main
    vllm pipeline_tag: audio-text-to-text Voxtral Small 1.0 (24B) - 2507 Voxtral Small is an enhancement of …vllm pipeline_tag: audio-text-to-text Voxtral Small 1.0 (24B) - 2507 Voxtral Small is an enhancement of Mistral Small 3 , incorporating state-of-the-art audio input capabilities while retaining best-…

    huggingface.co

  • README.md · mistralai/Voxtral-Small-24B-2507 at 7bc0161908d21beeac6ee540fc2827109b7f6de1
    Eval Results arxiv: 2507.13264 License: apache-2.0 Model card Files Files and versions xet Community 28 …Eval Results arxiv: 2507.13264 License: apache-2.0 Model card Files Files and versions xet Community 28 Deploy Copy to bucket new 7bc0161 Voxtral-Small-24B-2507 / README.md patrickvonplaten's picture…

    huggingface.co

  • Mistral AI has announced 'Voxtral TTS,' a text-to-speech AI model that allows users to clone their own voice. It supports 9 languages, is incredibly fast, lightweight, and open-source. - GIGAZINE
    performance.' Another key feature of the model released this time is that it is provided …performance.' Another key feature of the model released this time is that it is provided as 'open weights.' This means that developers can freely download the model and run and modify it in their own…

    gigazine.net

  • mistralai/Voxtral-Mini-4B-Realtime-2602 · Update README.md
    mistralai / Voxtral-Mini-4B-Realtime-2602 like 943 Follow Mistral AI_ 18.9k Automatic Speech Recognition Safetensors 13 languages …mistralai / Voxtral-Mini-4B-Realtime-2602 like 943 Follow Mistral AI_ 18.9k Automatic Speech Recognition Safetensors 13 languages vllm voxtral_realtime mistral-common Eval Results arxiv: 2602.11298 L…

    huggingface.co

Also known as: mistral/voxtral-small-2507

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works