jev-voice-browser

Project facts

Relationship to Jev

Jev application

Evidence

Documented

Language

JavaScript

License

MIT

Origin

Original repository

Repository status

Not archived

Created

2026-09-20

GitHub stars

0

Evidence checked

2026-09-24T08:40:10.508Z

Metadata checked

2026-09-24T08:40:10.508Z

Check status

current

Stars measure the whole repository, including work unrelated to Jev.

Evidence and scope

Documented records the linked documentation or source. JevHunt has not independently run or benchmarked this project.

Speech is streamed either directly from the **browser microphone (48kHz s16le PCM via Web Audio API + WebSocket)** or from a local **Doubao Voice Bridge** (TCP 4387 & TCP 5004); on every partial transcript the server asks **Jev** (TypeSafe's System One model, `jev-1.13.0`) one request with a dozen typed questions — intent, target element, site, "is the command complete?", "is this even addressed to me?", "is it destructive?" — gets typed probabilities back in ~250–350 ms, and code decides whethe

Evidence commit: 84597ae710fca9e99d47a6b259d7830d059e4f7d

Discovered through: github-search.