Skip to content
JevHub

[ Built with Jev · Voice control ]

voice-browser: it acts before you finish the sentence

Controls a real browser by voice, word by word.

By Moritz Kremb (@moritzkremb on GitHub) ·

jev-voice-browser

moritzkremb

GitHub preview of moritzkremb/jev-voice-browser

How it uses Jev

On every partial transcript, Jev answers a dozen questions (intent, target, is the command complete, is it destructive) in about 300 ms, and code decides whether to act, wait or ask.

Summary written by JevHub. Figures are the author's own; we haven't reproduced them. The project belongs to its author.

More builds

Andy Gao

@instantricecook

I built a voice controlled computer-use for my mac using @typesafeai's Jev and it's INSANE how fast it is! I can dictate "open the notes app and create..." and the app opens before I even finish my sentence.

6.2Klikes on X

Pratim Bhosale

@BhosalePratim

Played around with @typesafeai Jev today, mostly to understand what it does for tool calling. Instead of an LLM deciding what to do, I substituted that part with Jev. My learning is that we will be able to make the agent act before the user finishes the sentence. So far,

478likes on X

mikegee

@mikegee

Controlling Figma with voice using Jev from @typesafeai Total cost from first line of code to recording this video: $0.01 🤯

169likes on X