A high-performance text-to-speech skill leveraging the Microsoft Edge voice engine for natural, multilingual audio generation via AI agents.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install edge-tts-global
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 edge-tts-global 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 Edge TTS Global?
Edge TTS Global is a powerful extension for AI agents that utilizes the globally installed edge-tts engine to convert text into high-quality, natural-sounding audio. It is designed to provide immediate voice synthesis capabilities, particularly optimized for Chinese and multilingual outputs. By integrating this into the Openclaw Skills ecosystem, developers can give their agents the ability to communicate through audio dynamically.
The skill provides a streamlined workflow for generating MP3 files and subtitles, supporting both direct command-line execution and a specialized Python helper script. Whether you need Telegram-style voice bubbles or standard audio attachments, Edge TTS Global handles the creation, delivery, and automated cleanup of media assets efficiently.
Edge TTS Global Use Cases
- Creating natural-sounding voice messages for Telegram using the asVoice property.
- Generating high-quality Chinese (Mandarin) audio using the zh-CN-XiaoxiaoNeural voice.
- Automated generation of audio files with accompanying VTT subtitles for video accessibility.
- Quick text-to-speech prototyping within AI agent workflows.
- Multilingual audio content creation for automated alerts or notifications.
How Edge TTS Global Works
- The AI agent receives a text string and identifies the target language and voice preference.
- The skill utilizes the tts_edge.py helper script or calls the edge-tts command directly to process the request.
- Audio files are generated and stored temporarily in the workspace temp directory to maintain isolation.
- If subtitles are requested, the engine generates a .vtt file alongside the .mp3 output.
- The agent delivers the file to the user (e.g., via Telegram voice bubble or standard attachment).
- Upon successful delivery, a cleanup routine is triggered to delete the temporary media files and maintain workspace hygiene.
Edge TTS Global Setup
To utilize this skill within the Openclaw Skills environment, ensure the edge-tts package is installed on your system.
# Install the core engine
pip install edge-tts
# Ensure the skill directory is accessible
cd /data/claw/shared/skills/edge-tts-global
Verify the installation by listing available voices:
edge-tts --list-voices
Edge TTS Global Data Schema & Taxonomy
The skill manages data within the current caller workspace, adhering to a strict temporary lifecycle.
| File Type | Default Location | Description |
|---|---|---|
| Audio Output | ./temp/*.mp3 |
The generated voice file. |
| Subtitles | ./temp/*.vtt |
Optional WebVTT subtitle file. |
| Scripts | scripts/tts_edge.py |
Internal logic for streamlined generation and cleanup. |
Metadata such as voice selection (e.g., zh-CN-XiaoxiaoNeural) and speech rate are passed as arguments during the execution phase.
Edge TTS Global Advanced Features
- Smart Cleanup: Specialized cleanup commands to remove both audio and subtitle files in a single execution.
- Telegram Integration: Support for asVoice=true to transform standard MP3s into native voice-bubble messages.
- Subtitle Synchronization: Concurrent generation of VTT files for perfectly timed text overlays.
- Custom Voice Mapping: Ability to toggle between hundreds of Microsoft Edge's neural voices via CLI arguments.
- Workspace Isolation: Strict adherence to local temp directories to prevent file collisions in multi-agent environments.
SKILL.md
Loading
Related Openclaw Skills
Positive Psychology Companion
An evidence-based AI assistant designed to enhance well-being and psychological resilience through the lens of Positive Psychology.
Java Maven Secondary Analysis
A professional auditing tool for Java Maven projects to identify secondary development scope, module distribution, and architectural risks.
AI X-Ray Clothes Skill
An advanced AI-powered image processing skill that transforms clothing into sheer, see-through materials through automated fabric segmentation and rendering.
Bald Filter Skill
An AI-powered image processing skill that makes subjects appear bald while maintaining high-fidelity facial features.
Java Maven Code Review
An automated auditing tool for Java Maven projects that generates detailed reports on code quality, module boundaries, and project structure.
GetNote: Personal Knowledge & Note Management
A professional-grade personal knowledge management skill that enables AI agents to save, search, and organize notes, images, and links.
Featured*
