Audio model

Voxtral Mini 4B Realtime 2602

4B-parameter multilingual streaming ASR model for real-time transcription and translation across 13 languages, delivering sub-500 ms latency with open weights suitable for on-device or server use.

Type
Audio
Weights
Open
Downloads
1.8M
Likes
992
Pipeline
automatic speech recognition
License
apache-2.0

Model hub

mistralai/Voxtral-Mini-4B-Realtime-2602

Repo
mistralai/Voxtral-Mini-4B-Realtime-2602
Library
vllm
Access
Public
Technical tags and languages
en fr es de ru zh ja it pt nl ar hi ko vllm safetensors voxtral_realtime mistral-common automatic-speech-recognition base_model:mistralai/Ministral-3-3B-Base-2512 base_model:finetune:mistralai/Ministral-3-3B-Base-2512 eval-results
Open on Hugging Face

Papers

1

More from Mistral AI

13

About Mistral AI

1

Mistral AI develops frontier generative AI models, infrastructure, and enterprise deployment products.