voiceclaw
by @kentoku24
Voice conversation interface for OpenClaw using wake word detection, streaming LLM responses, and text-to-speech. Use when a user wants to talk to their Open...
# Install
git clone https://github.com/kentoku24/voiceclaw.git
cd voiceclaw
npm installStart (no .env needed if OpenClaw is running locally)
npm start
β [voiceclaw] OpenClaw config loaded from ~/.openclaw/openclaw.json
β [voiceclaw] listening on http://127.0.0.1:8788
Open browser
open http://127.0.0.1:8788
Press ιε§, say the wake word (default: γ’γͺγΉ), then speak your command.
All settings are optional. Set in .env or environment variables:
| Variable | Default | Description |
|---|---|---|
| WAKE_WORDS | γ’γͺγΉγ‘γγ,γ’γͺγΉ,... | Comma-separated wake words |
| STT_LANG | ja-JP | Speech recognition language |
| OPENCLAW_MODEL | openclaw | LLM model name |
| VOICEVOX_URL | http://127.0.0.1:50021 | VOICEVOX endpoint |
| VOICEVOX_SPEAKER | 1 | VOICEVOX speaker ID |
| HOST | 127.0.0.1 | Server bind address |
| PORT | 8788 | Server port |
Gateway token is auto-detected from ~/.openclaw/openclaw.json. Override with OPENCLAW_GATEWAY_TOKEN if needed.
clawhub install voiceclaw-jp