Docs / source reviewed
Jev Voice
Turn spoken commands into bounded macOS actions
How this project uses Jev
- Input
- Speech transcripts, the frontmost app, installed-app candidates and split command clauses
- Jev decides
- Action type, target app, system action and whether a clause refers to the foreground app or a URL
- Code executes
- Local parsing extracts URLs, text and values; macOS tools launch apps, dictate and perform system actions, with confirmation for ambiguous commands
Evidence and limitations
Common commands may run through local rules; on-device transcription depends on system support. Jev neither generates argument text nor hears audio. System permissions are required, and we did not install or validate live voice control.
This project has not been run independently here. Author-reported results are not independently verified results.
Original sources
- https://github.com/chris-wozniczek/jev-voice-control/blob/0f51d927db50383b05705bac225795b5e6048f28/README.md ↗
- https://github.com/chris-wozniczek/jev-voice-control/blob/0f51d927db50383b05705bac225795b5e6048f28/Sources/JevVoiceCore/JevClient.swift ↗
- https://github.com/chris-wozniczek/jev-voice-control/blob/0f51d927db50383b05705bac225795b5e6048f28/Sources/JevVoiceCore/CommandInterpreter.swift ↗