mistralai/Voxtral-Small-24B-2507

Audio Text To Text·mistralai· 108.5K· 504

vllm apache-2.0 Audio Text To Text 24.3B params

Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding.

Open in MLForge Sign up free Desktop app Source ↗

# pull & run locally
pip install mlforge-sdk && mlforge pull mistralai/Voxtral-Small-24B-2507

Model details

Task

Audio Text To Text

Provider

mistralai

Framework

vllm

Parameters

24.3B

Size

90 GB

License

apache-2.0

Downloads

108.5K

Likes

504

Paper

arXiv:2507.13264

Updated

2025-12-20

About mistralai/Voxtral-Small-24B-2507

Related Audio Text To Text

U fixie-ai/ultravox-v0_5-llama-3_2-1b Audio Text To Text ·683.1M params 1.1M 88 🤗 HF Q Qwen/Qwen2-Audio-7B-Instruct Audio Text To Text ·8.4B params 670.1K 543 🤗 HF V microsoft/VibeVoice-ASR-HF Audio Text To Text ·8.3B params 665.1K 156 🤗 HF U fixie-ai/ultravox-v0_6-llama-3_1-8b Audio Text To Text ·687.3M params 645.4K 6 🤗 HF A nvidia/audio-flamingo-3-hf Audio Text To Text ·8.3B params 271.0K 187 🤗 HF M nvidia/music-flamingo-2601-hf Audio Text To Text ·8.3B params 194.9K 106 🤗 HF

Browse all Audio Text To Text models →