Skip to content
JevDirectory.org
CommunityTools & Integrations143 starsVerified 2026-09-20

voice-browser

Control a headed Chromium window by voice: one Jev request per partial transcript decides intent, target, and completeness in roughly 300 ms, while code applies thresholds and builds the action.

Category
Tools & Integrations
Published by
Community
Author
moritzkremb
Added
2026-09-20
Tagscommunityjavascriptbrowservoiceplaywright

Highlights

  • One Jev request per partial transcript with 9 to 11 typed questions, replying in about 250 to 350 ms.
  • Actions: navigate, search, click, type, scroll, history, tabs, confirm, and cancel.
  • Ambiguous targets get numbered page overlays, and a spoken number picks one without a model call.
  • Destructive clicks require a spoken confirmation before the action fires.

Watch out

Requires Chrome or Edge for the Web Speech API (Firefox and Safari are unsupported), Node 20 or newer, and a TypeSafe key.

More like this

A browser-use agent where Jev picks one action per step from a page's interactive elements. Runs as an MCP server, CLI, or library and returns a step trace, screenshot, and console errors.
Tools & Integrations#community#typescript#mcp
Communityjev-browser
Grep by meaning instead of regex: Jev scores every line, meanings combine with AND, OR, and NOT, and one query matches across Japanese, French, German, Spanish, and more.
Tools & Integrations#community#javascript#cli
Communityjev-semgrep
Browser Use's Ultrafast agent puts Jev in charge of picking each browser action from a dynamic DOM action space. The author reports a flight search in 7 seconds for about $0.0039.
Tools & Integrations#community#x#video
Community
Back to all resources

From the community

Posts from builders shipping with Jev right now.

700 leads scored for $0.09

Beating Gemini Flash Lite on an eval