Live captions on smart glasses

Last checked: 2026-11-08. Verification: the example server and glasses web page ran locally, the Even G2 plugin ran in the official Even Hub simulator; nothing in this skill ran on glasses yet. Vendor facts are docs-only unless marked.

This skill assumes the target glasses are known. If they are not, start with the smart-glasses skill (which glasses, which rung of the display-text ladder, vendor SDK pointers). The rungs used below: 1 vendor SDK, 2 web app on the glasses, 3 USB-C display glasses as an external display, 4 phone notification mirrored by the glasses' app, 5 voice in the ear.

The pipeline

microphone ─► VAD ─► streaming STT ─► caption events ─► transport ─► line fitter ─► glasses display
 (phone or     (drop     (partial and      seq, text,      WebSocket,   per display     (SDK, web page,
  glasses)     silence)   final results)   final           HTTP poll    budget          USB-C, notification)
                                                └──────────► short hint ─► text-to-speech ─► ear