Voxtral is a web application that allows users to upload audio files, select a transcription model and language, and receive written text output. It is suitable for students, professionals, and anyone needing accurate speech-to-text conversion.
Voxtral is an AI project. It focuses on converting speech from audio files into accurate written text in various languages. It is built as a consumer product for students and professionals needing transcription. Voxtral is free to use. It runs on the web, and it can be self-hosted.
Behind Voxtral is MohamedRashad, and it first shipped in 2024. Among its 5 catalogued features are audio transcription, language selection, and model selection.
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