9d2ffd1b0d4f76aac58026fd2cc16ca207325a48
on_audio was resetting the timer on every chunk including silence, so the timeout never fired. Now passes the raw chunk and checks RMS; only resets if energy is above 0.02 (speech, not ambient silence). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Description
Voice pipeline experiment: local STT/TTS interface for Claude Code. Published for transparency — work in progress.
Languages
JavaScript
78.8%
Python
14.4%
Shell
6.8%