Jev Voice Browser

Speak or type instructions into a local web page, then use a headed Playwright Chromium browser for navigation, clicking, and typing. The project converts incrementally received speech-recognition text into structured intent and requires confirmation for destructive actions. Requires Node, microphone support in Chrome or Edge, and a TypeSafe API key. Source code is available at no charge; hosted features, online models, and third-party services may have separate fees. Sources: https://github.com/moritzkremb/jev-voice-browser/blob/main/README.md https://www.jev.store/projects/jev-voice-browser Only source code or documentation was reviewed. The application was not installed or run, and its effectiveness was not verified.