What it does
Split local Laya batches across Apple Neural Engine and GPU with a Jev-shaped API; it accelerates an independent model, not Jev.
Benchmarks & research
Only you can see your notes.
Screenshot unavailable. Open the experiment ↗
Split local Laya batches across Apple Neural Engine and GPU with a Jev-shaped API; it accelerates an independent model, not Jev.
Start by writing a list of spoken voice commands and the Mac actions they should trigger. You can also write questions to sort incoming messages, like choosing which team handles each note. A developer can then set up this software on your computer to match transcripts to those actions.
This tool is built specifically for modern Apple computers. It splits the work between your Mac's graphics chip and neural processor so it can answer quickly. Everything runs entirely on your own machine, keeping your personal transcripts and requests away from outside servers.