mikael-lovqvists-claude-agent/claude-voice-experiment
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
4 Commits 1 Branch 0 Tags
8604d7ea51645ee22a25a6f5864fa0e946f758b9
Go to file
Clone
Open with VS Code Open with VSCodium Open with Intellij IDEA
Download ZIP Download TAR.GZ Download BUNDLE
mikael-lovqvists-claude-agent 8604d7ea51 Debounce speech detection — require 3 consecutive loud chunks (~150ms) 
A single transient noise no longer resets the silence timer.
Only sustained audio energy counts as speech.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-30 05:12:03 +00:00
demos
Initial commit — voice pipeline experiment
2026-05-30 04:48:54 +00:00
lib
Fix silence timeout never firing — gate on audio amplitude
2026-05-30 05:09:20 +00:00
.gitignore
Initial commit — voice pipeline experiment
2026-05-30 04:48:54 +00:00
acting-demo-bark.mjs
Initial commit — voice pipeline experiment
2026-05-30 04:48:54 +00:00
acting-demo-chatterbox.mjs
Initial commit — voice pipeline experiment
2026-05-30 04:48:54 +00:00
acting-demo.mjs
Initial commit — voice pipeline experiment
2026-05-30 04:48:54 +00:00
bark-server.py
Initial commit — voice pipeline experiment
2026-05-30 04:48:54 +00:00
chatterbox-server.py
Initial commit — voice pipeline experiment
2026-05-30 04:48:54 +00:00
CLEANUP-PLAN.md
Initial commit — voice pipeline experiment
2026-05-30 04:48:54 +00:00
demo-bark.mjs
Initial commit — voice pipeline experiment
2026-05-30 04:48:54 +00:00
demo-kokoro.mjs
Initial commit — voice pipeline experiment
2026-05-30 04:48:54 +00:00
download-models.sh
Initial commit — voice pipeline experiment
2026-05-30 04:48:54 +00:00
listen.mjs
Initial commit — voice pipeline experiment
2026-05-30 04:48:54 +00:00
LLM-ROUTING.md
Initial commit — voice pipeline experiment
2026-05-30 04:48:54 +00:00
NOTES.md
Initial commit — voice pipeline experiment
2026-05-30 04:48:54 +00:00
package.json
Initial commit — voice pipeline experiment
2026-05-30 04:48:54 +00:00
query-demo.mjs
Debounce speech detection — require 3 consecutive loud chunks (~150ms)
2026-05-30 05:12:03 +00:00
requirements.txt
Initial commit — voice pipeline experiment
2026-05-30 04:48:54 +00:00
setup-venv.sh
Initial commit — voice pipeline experiment
2026-05-30 04:48:54 +00:00
speak-as.mjs
Initial commit — voice pipeline experiment
2026-05-30 04:48:54 +00:00
SPEAKER-DIARIZATION.md
Initial commit — voice pipeline experiment
2026-05-30 04:48:54 +00:00
TODO.md
Initial commit — voice pipeline experiment
2026-05-30 04:48:54 +00:00
tts-server.mjs
Initial commit — voice pipeline experiment
2026-05-30 04:48:54 +00:00
voice-buddy.mjs
Initial commit — voice pipeline experiment
2026-05-30 04:48:54 +00:00
VOICES.md
Initial commit — voice pipeline experiment
2026-05-30 04:48:54 +00:00
voices.yaml
Initial commit — voice pipeline experiment
2026-05-30 04:48:54 +00:00
Description
Voice pipeline experiment: local STT/TTS interface for Claude Code. Published for transparency — work in progress.
108 KiB
Languages
JavaScript 78.8%
Python 14.4%
Shell 6.8%