mirror of
https://github.com/DeeJanuz/frametop.git
synced 2026-10-17 19:00:38 +02:00
The mic's one-second sample goes to whisper-server with curl, as ft-voiced sends it. Only the HTTP status, time and word count are kept. A clip of silence is flagged, since whisper invents words for it. frame-voice's units and logs are included when it is installed, since it uses the same mic and port. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>