jev / gallery
← Back to collection

Docs / source reviewed

Jev Voice Browser

Choose browser actions while the user speaks

How this project uses Jev

Input
Live partial transcripts and page-element snapshots
Jev decides
Intent, target, command completeness, and risk
Code executes
Local policy chooses execute, wait, confirm, or ignore

Evidence and limitations

Other components transcribe speech and control the browser. Author latency/cost figures were not reproduced here; spoken confirmation is not a safety guarantee.

This project has not been run independently here. Author-reported results are not independently verified results.

Original sources

Explore related use cases

Browse this category →