What it does
Speech recognition happens on-device, and only the transcript is sent to Jev. macOS accessibility permission is required.
Apps & data pipelines
Jev Voice
Press a macOS shortcut, speak a command, and let Jev route it to a bounded app, typing, volume, or interface action.
Bookmark: Jev Voice
Keep this in your collection.
Leave a noteWhat would you try with this?
: Jev Voice
Only you can see your notes.
Screenshot unavailable. Open the experiment ↗
How you can use it
A developer can adapt this Mac application to turn spoken words into computer actions. The software listens to a user and turns their speech into text directly on the computer. It then sends only that written text to Jev, an outside AI service.
Jev decides what the text means so the application can act. For example, it might open a website, close a program, or type a message. A developer needs an access key that connects the application to TypeSafe. The computer must also grant permission to control the screen.