Add ElevenLabs voice replies so the bot responds to voice notes with voice notes.
When someone sends a voice note, the bot replies with a voice note instead of text. Uses ElevenLabs TTS.
Ask the user to:
Add to .env:
ELEVENLABS_API_KEY=<key>
Ask: "Which voice should the bot use? You can browse voices at elevenlabs.io/voice-library, or use a custom/cloned voice."
If they have a specific voice, get the voice ID from the ElevenLabs dashboard. If not, suggest they browse the library and pick one that fits.
Add to .env:
ELEVENLABS_VOICE_ID=<voice_id>
If they skip this, the default voice will be used.
npm run build
launchctl kickstart -k gui/$(id -u)/com.ghostclaw # macOS
# systemctl --user restart ghostclaw # Linux
Tell the user to send a voice note to the bot. It should reply with a voice note using the selected voice. Text messages still get text replies.
The bot detects when an incoming message is a voice note (tagged [Voice: ...] after transcription). When replying to a voice message, it converts the text response to audio via ElevenLabs TTS and sends it as a voice note. Text messages always get text replies.
Remove ELEVENLABS_API_KEY from .env and restart. The bot will fall back to text replies for everything.
Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Start voice calls via the OpenClaw voice-call plugin.
Notion API for creating and managing pages, databases, and blocks.
Gemini CLI for one-shot Q&A, summaries, and generation.
Category:developer