Setup & Installation
openclaw skills install @xadenryan/clawdbot-skill-voice-wake-say
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install clawdbot-skill-voice-wake-say
What This Skill Does
Reads assistant responses aloud on macOS using the built-in `say` command. Triggers only when the user message starts with the exact phrase "User talked via voice recognition on m3". Each message is checked independently; context from prior messages does not carry over.
Uses the local macOS `say` command instead of cloud TTS providers, so responses are spoken with no API calls, no latency, and no external dependencies.
When to use it
- Hearing a spoken acknowledgment before a long task begins
- Listening to a response while away from the screen
- Hands-free confirmation that a voice command was received
- Getting a short spoken summary when the full response is code-heavy
- Audible task completion notification after a background job finishes
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User talked via voice recognition on m3: set a reminder to review the pull request
AGENT
- 1Detects the Voice Wake trigger phrase at the start of the message
- 2Calls `say` to acknowledge receipt before starting the task
- 3Processes the reminder request
- 4Strips any markdown from the response text
- 5Calls `say` again to speak a brief summary of what was done
OUTPUT
Spoken acknowledgment and completion message; full response text also displayed on screen