Voxtral-Mini-3B is a 3 billion parameter multimodal foundation model developed by Mistral AI. It excels at audio understanding, automatic speech recognition, and related tasks. The model supports inference through the Transformers library or vLLM and is evaluated on standard ASR benchmarks. It is fully open weights for local or cloud deployment.
Voxtral Mini 3B 2507 sits in PulseGate's Multimodal & vision category. It focuses on processing and understanding spoken audio content with high accuracy using a compact open model. Voxtral Mini 3B 2507 is an open-source project aimed at developers. Voxtral Mini 3B 2507 is open source under the Apache-2.0 license. It ships for the web, the command line, and API.
It is developed by Mistral AI, and it first shipped in 2023. The project is developed in the open on GitHub with 86.6k stars and 3k commits in the last 90 days. Key capabilities include Audio Understanding, Speech Recognition, and multimodal.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do