Control your Mac's voice remotely from mobile devices to play announcements, alarms, and stories using high-quality neural TTS.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install callmac
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install callmac using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Callmac: Remote Voice Control for Mac?
Callmac is a sophisticated tool within the ecosystem of Openclaw Skills designed to provide remote voice control capabilities for macOS. By integrating messaging platforms like Telegram or WhatsApp with your Mac, it allows you to trigger text-to-speech commands from anywhere in the world. Whether you need to broadcast a quick announcement, set a verbal alarm, or play a story for your children, this skill makes it possible via a simple mobile interface.
Built on top of the powerful edge-tts engine, Callmac supports high-quality neural voices that sound natural and professional. One of the standout features of these Openclaw Skills is the native support for mixed language content, allowing for seamless transitions between Chinese and English in a single sentence. It leverages native macOS utilities like afplay and osascript to ensure low-latency playback and precise volume control directly on your hardware.
Callmac: Remote Voice Control for Mac Use Cases
- Broadcasting urgent remote announcements to a home or office Mac from a mobile device.
- Triggering verbal wake-up calls or reminders for family members while you are away.
- Creating automated, scheduled reminders for meetings that play through the Mac's internal speakers.
- Generating high-quality mixed-language audio files for presentations or educational content.
- Using SSML to create complex audio scripts with specific pauses and emphasis for notifications.
How Callmac: Remote Voice Control for Mac Works
- The user sends a command such as /callmac followed by text through a supported messaging client connected to Openclaw Skills.
- The system analyzes the text to detect language segments, identifying which parts are English and which are Chinese.
- The generate_tts.py script communicates with the edge-tts service to synthesize the text into high-quality neural audio.
- If immediate playback is requested, the skill uses the macOS afplay utility to output audio through the system speakers.
- Volume levels are dynamically adjusted using osascript to ensure the announcement is heard at the correct level.
- For complex tasks, multiple audio segments are concatenated using ffmpeg to create a unified MP3 file.
Callmac: Remote Voice Control for Mac Setup
To get started with these Openclaw Skills, ensure you have Python and Homebrew installed on your Mac.
# Install the edge-tts engine for high-quality synthesis
pip3 install edge-tts
# Install ffmpeg for audio merging capabilities
brew install ffmpeg
# Verify that the voices are accessible
python3 -m edge_tts --list-voices
Callmac: Remote Voice Control for Mac Data Schema & Taxonomy
Callmac manages audio generation and playback through a structured set of scripts and file outputs as part of the Openclaw Skills framework:
| Component | Description | Data Format |
|---|---|---|
| Generated Audio | The result of the TTS synthesis process | .mp3 |
| Playlists | Text files used to batch process or merge audio segments | .txt |
| System Controls | Volume and playback state managed via AppleScript | Integer/Boolean |
| Metadata | Voice selection, speech rate, and pitch parameters | CLI Arguments |
Callmac: Remote Voice Control for Mac Advanced Features
- Intelligent mixed-language detection that automatically assigns the best neural voice for English and Chinese segments.
- Full SSML support allowing developers to insert breaks, change pitch, and adjust speech rates for professional-grade audio.
- Loop playback functionality to ensure critical alerts are repeated until acknowledged.
- Remote volume management that can override current system settings to ensure announcements are audible.
- Batch processing scripts to merge multiple generated files into a single playlist or long-form audio file.
SKILL.md
Loading
Related Openclaw Skills
SiliconFlow Provider Configuration
A comprehensive configuration skill to integrate SiliconFlow's inference platform into OpenClaw for access to over 98 AI models including DeepSeek, Qwen, and Kimi.
NewCLI Model Provider Configuration
A configuration skill for integrating NewCLI as a multi-model provider for OpenClaw, featuring high-efficiency AWS routes for Claude models.
MiniMax Provider Configuration
A technical skill for integrating MiniMax M2.1 series models into OpenClaw using both direct API Key and OAuth portal access methods.
Spacesuit Framework for OpenClaw
A batteries-included framework scaffold designed to standardize and secure AI agent workspaces.
OpenClaw Starter Guide
A strategic roadmap for deploying, configuring, and optimizing cost-effective multi-agent AI systems from zero to professional scale.
trainedby-mcp Personal AI Coach
A personal AI coaching skill that connects health data, fitness goals, and training reflections to your AI agent via the trainedby.ai MCP server.
Featured*
