jev-voice-browser: speech → finite actions → code
You should be able to explain jev-voice-browser in four sentences: what enters the system, what Jev judges, what code executes, and what independently proves the job finished.
Use caseLimit browser or computer actions to reviewable choices
Voice-driven browsing fails when “whatever was heard” executes. Map speech to CLICK/TYPE/SCROLL/DONE first; deterministic code runs next. Boundary and acceptance notes from the public repo.
Source · moritzkremb/jev-voice-browser · Open-source project
What this project does
Section titled “What this project does”A mic wired to arbitrary scripts can submit forms on one misheard word. Safe path: speech → finite Choice → code → done condition.
Sources
Section titled “Sources”
GitHub Open Graph preview for the moritzkremb/jev-voice-browser repository; a repository preview, not a screenshot of running software. Notes are based on its public source.
A useful first read
Section titled “A useful first read”Limit browser or computer actions to reviewable choices
Based on the public repository; this site has not reproduced the full project. Read the source before deciding whether to try it.