moritzkremb/jev-voice-browser
VerifiedJev applicationDocumented
jev-voice-browser (moritzkremb) uses Jev to turn partial speech transcripts into bounded Playwright actions; code selects when to act and copies text candidates literally.
jev-voice-browser streams speech transcripts to a Node server controlling a visible Chromium window through Playwright.
Jev selects intent and targets; code extracts literal text candidates and decides whether to act, wait or ask.
Use Node 20+, a TypeSafe key and Chrome or Edge for the microphone control page.
Speech recognition sends audio to Google. Page snapshots omit iframes and cap visible candidates at 100 elements.
Evidence checked:
Control a real browser by voice. Jev (TypeSafe System One) decides intent + target in ~300 ms per spoken word; Playwright acts — often before you finish the sentence.
Stars measure the whole repository, including work unrelated to Jev.
Documented records the linked documentation or source. JevHunt has not independently run or benchmarked this project.
Evidence commit: 198a0764395a666f8398026c0d8abdaf6d1866c5
Discovered through: awesome-jev, typesafe-field-guide.
How we review →Suggest a correction · Claim this listing · Submit a project