Whisper WebGPU is a browser-based transcription app that lets users upload or record audio and convert speech into text. It runs Whisper inference locally with WebGPU and supports copying or downloading the resulting transcript.
Whisper WebGPU is a Speech to text project. It focuses on transcribing spoken audio without sending recordings to a remote transcription service. Whisper WebGPU is an open-source project aimed at people needing quick browser-based audio transcription. Whisper WebGPU costs nothing to use. It ships for the web.
Behind Whisper WebGPU is Xenova. Key capabilities include audio upload, audio recording, and speech transcription.
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