A lightweight macOS text-to-speech skill utilizing the native say command for voice notifications and audio alerts.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install mac-tts
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 mac-tts 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 mac-tts?
The mac-tts skill is a specialized utility designed to bring native voice capabilities to your local environment. By leveraging the built-in macOS say command, this entry in the Openclaw Skills library allows for high-fidelity audio output without needing external cloud APIs. It is perfect for developers who want to integrate voice-based feedback, status reports, or accessibility features directly into their local automation workflows.
This skill supports a diverse array of international voices, making it highly versatile for global applications. Whether you are building a personal assistant or a sophisticated monitoring tool, mac-tts provides the reliable audio layer needed for professional Openclaw Skills implementations on Apple hardware.
mac-tts Use Cases
- Creating audible system notifications for incoming webhooks or local triggers.
- Implementing voice alerts for developer tools and long-running build processes.
- Providing multilingual support for reading text aloud in Mandarin, English, or Japanese.
- Enhancing accessibility by vocalizing screen text and status updates within Openclaw Skills.
- Setting up localized voice announcements for smart home or office environments.
How mac-tts Works
- The user or agent triggers the skill with a text payload and optional voice selection.
- The system checks for the availability of the specified voice using native macOS utilities.
- Volume levels are optionally verified or adjusted using AppleScript integration to ensure the message is heard.
- The mac-tts skill executes the say command, converting the text into high-quality audio.
- Audio is played through the default system speakers either synchronously or in the background.
mac-tts Setup
Ensure you are using a macOS environment. This skill requires no additional packages as it uses native system tools. To test your installation within the Openclaw Skills ecosystem, run:
say "Testing the mac-tts integration"
To configure volume via CLI:
osascript -e "set volume output volume 70"
mac-tts Data Schema & Taxonomy
The mac-tts skill utilizes standard system arguments to manage speech synthesis. Below is the organizational structure for data handled by this skill:
| Attribute | Description | Example |
|---|---|---|
| message | The raw text to be converted to speech | "Hello World" |
| voice_id | The specific identifier for the macOS voice | "Meijia" |
| sync_mode | Determines if the process blocks or runs in background | "&" for async |
| volume_level | System output volume control (0-100) | 70 |
All metadata and configurations are handled through standard macOS environment variables and shell arguments.
mac-tts Advanced Features
- Support for asynchronous execution using shell backgrounding to prevent workflow interruption.
- Detailed voice filtering allowing users to list and select specific regional dialects like zh_TW.
- Deep integration with osascript for fine-grained control over system audio states and muting.
- Zero-latency processing as a native Openclaw Skills component, requiring no internet connectivity for speech generation.
- Compatibility with all native macOS voices, including those downloaded via System Settings.
SKILL.md
Loading
Related Openclaw Skills
Proton Pass CLI
A powerful command-line interface for managing Proton Pass vaults, items, and injecting secrets into development workflows.
ClawDraw
A WebGPU-powered multiplayer canvas for AI agents to create algorithmic art and paint images.
ClawDraw
A WebGPU-powered multiplayer canvas that enables AI agents to create algorithmic art, paint images, and collaborate in real time.
ClawDraw
ClawDraw is an advanced generative art skill that enables AI agents to create complex algorithmic patterns and transform images into artistic strokes on a real-time multiplayer canvas.
Voice Transcription Skill
A high-performance, local voice-to-text transcription tool leveraging Faster Whisper for privacy-conscious workflows.
Moltpad
Moltpad is an advanced AI agent skill designed for reading, writing, and publishing literary content within the Moltpad.space community.
Featured*
