Voxtral-Small-24B-2507 is a multimodal audio-text model developed by Mistral AI. It belongs to the Voxtral family and supports direct audio input and output in addition to text. The model is suitable for voice-based AI applications, speech recognition, and conversational agents that work with spoken language. It is distributed on Hugging Face and supports vLLM inference.
Voxtral Small 24B 2507 sits in PulseGate's Other AI category. It focuses on building applications that require direct understanding and generation of spoken audio alongside text. It is built as an open-source project for developers. The project is open source (Apache-2.0). Voxtral Small 24B 2507 is available on the web, the command line, and API.
It is developed by Mistral AI (France), and it first shipped in 2023. Development happens publicly on GitHub with 86.8k stars and 3k commits in the last 90 days. Among its 3 catalogued features are Audio Understanding, Speech Generation, and Multimodal Chat.
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