mac-tts

What This Skill Does

The mac-tts skill is a powerful, lightweight utility that interfaces directly with the native macOS say command. It enables OpenClaw AI to provide audible, natural-sounding feedback directly through your computer's speakers. By tapping into the high-quality speech synthesis engines integrated into macOS, this skill allows for seamless text-to-speech output without the need for external API keys or expensive cloud subscriptions. It supports a vast array of global languages and voices, making it ideal for localized notifications and multilingual accessibility.

Installation

To integrate this skill into your environment, run the following command in your terminal:

clawhub install openclaw/skills/skills/kalijason/mac-tts

Ensure that your OpenClaw environment has the necessary permissions to execute system-level shell commands, as this skill utilizes the native macOS binary environment to generate audio output.

Use Cases

This skill is designed for scenarios where auditory feedback is more effective than visual alerts. Common use cases include:

• Automated Task Completion: Use the skill to confirm that a complex automation or code deployment has finished successfully, allowing you to focus on other work without constantly monitoring the terminal.
• Calendar and Meeting Reminders: Configure the agent to announce upcoming meetings five minutes before they start, providing a helpful prompt that breaks your focus from deep work.
• Urgent System Alerts: Set up custom triggers to read out incoming high-priority messages or system errors, ensuring you never miss a critical update.
• Multilingual Support: Leverage specific voices like 'Meijia' for Traditional Chinese or 'Samantha' for English to maintain consistent and context-appropriate feedback in multilingual environments.

Example Prompts

1. "Use the mac-tts skill to say 'Task completed successfully' using the Meijia voice."
2. "Whenever my code compilation finishes, can you use mac-tts to announce 'The build is ready' through the speakers?"
3. "Please read out my next calendar event notification in a natural voice at 70 percent volume."

Tips & Limitations

• Synchronicity: By default, the say command is synchronous, meaning it will block other agent tasks until the speech finishes. For long passages, append an ampersand (&) to the command to run it in the background.
• Environment Constraint: This skill is strictly exclusive to macOS. Attempting to run it on Linux or Windows will result in an error.
• Volume Management: The agent can modify system volume using osascript. Ensure your system volume is set to an appropriate level before triggering alerts to avoid being caught off-guard.
• Voice Discovery: If you aren't sure which voice to use, run say -v "?" to list every available synthetic persona currently installed on your system.