Voxtral WebGPU is a browser-based audio transcription tool that uses WebGPU for fast, local speech-to-text conversion. It is ideal for journalists, researchers, and anyone needing quick audio transcription without uploading files to a server.
Voxtral WebGPU sits in PulseGate's Speech to text category. It focuses on transcribing audio to text efficiently in the browser without server-side processing. It is built as a consumer product for journalists and researchers. Voxtral WebGPU costs nothing to use. Voxtral WebGPU is available on the web.
It is developed by webml-community, and it first shipped in 2024. Key capabilities include audio transcription, webGPU acceleration, and browser-based processing.
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