Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Triggers voice announcements on a Mac from a mobile device by sending messages via Telegram or WhatsApp. Uses edge-tts to synthesize speech with automatic Chinese/English language detection, then plays audio locally through macOS. Supports looping, volume control, and scheduled playback.
Lets you play audio on a Mac without being physically present, using messaging apps you already have on your phone as the trigger.
When to use it
- Sending a wake-up call to kids from another room
- Broadcasting a dinner announcement throughout the house
- Playing a looping alarm reminder triggered from your phone
- Delivering bilingual announcements in Chinese/English households
- Scheduling repeated audio reminders via cron while away from the Mac
Example Workflow
Here's how your AI assistant might use this skill in practice.
User sends: /callmac 早饭好了！Breakfast is ready!
- 1Receives the message trigger from Telegram or WhatsApp
- 2Splits text into Chinese and English segments
- 3Generates TTS audio for each segment using matching neural voices
- 4Concatenates audio segments into a single MP3
- 5Plays the file on the Mac via afplay
Mac speakers play a bilingual announcement in the appropriate voices for each language
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.