What the tool does
The tool turns speech from audio into editable text with a browser-based Whisper model. Before transcription, the browser may prepare audio through a WASM decoder, download the model, and then use your computer or phone resources.
How to use it
- Add an audio file in a format supported by your browser.
- Choose a speech language, or keep automatic detection.
- Start transcription and watch the stages: audio preparation, model loading, recognition, and result.
- Review the text, edit it if needed, then copy it or download a TXT file.