A high-performance text-to-speech engine leveraging Microsoft Edge's neural voices to generate natural-sounding audio with deep customization options.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install edge-tts-cn
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-cn 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 Skill?
The Edge-TTS Skill is a robust integration designed for Openclaw Skills that enables seamless text-to-speech conversion using the node-edge-tts library. It provides developers and AI agents with the ability to transform written content into lifelike audio without requiring expensive API keys or complex authentication. By utilizing Microsoft Edge's neural TTS service, the skill delivers high-fidelity voice output suitable for a wide range of applications.
This skill is particularly powerful for creating accessible interfaces, automating content narration, or providing voice feedback in multi-agent environments. It supports granular control over audio parameters including voice selection, speaking rate, pitch, and volume, while also offering advanced features like word-level subtitle generation in JSON format.
Edge-TTS Skill Use Cases
- Automating the narration of long-form articles or search results for eyes-free consumption.
- Enhancing accessibility for users with visual impairments or reading difficulties.
- Generating high-quality voiceovers for social media content or presentations.
- Providing real-time audio feedback for hands-busy scenarios like cooking, driving, or hardware repair.
- Creating localized audio content across dozens of global languages and regional accents.
How Edge-TTS Skill Works
- The AI agent detects a tts trigger or specific user intent requesting audio output within the Openclaw Skills environment.
- The system pre-processes the input to filter out trigger keywords, ensuring only the target text is synthesized.
- A request is sent to the Microsoft Edge neural TTS service via the bundled Node.js scripts or built-in tools.
- The engine generates an MP3 audio file based on specified parameters such as voice ID, pitch, and rate.
- The skill returns a MEDIA path to the local audio file, which the hosting application then routes to the user's interface.
Edge-TTS Skill Setup
To get started with this skill, navigate to the scripts directory and install the necessary dependencies:
cd public/edge-tts/scripts
npm install
You can then verify the installation by running the built-in test suite:
npm test
Edge-TTS Skill Data Schema & Taxonomy
The skill manages data through configuration files and temporary storage paths to ensure efficiency within Openclaw Skills:
| Component | Path / Format | Description |
|---|---|---|
| Persistent Config | ~/.tts-config.json |
Stores default voice, rate, and pitch preferences. |
| Audio Output | /tmp/edge-tts-temp/ |
Default directory for generated MP3 files. |
| Subtitles | .json |
Optional word-level timing data for synchronized captions. |
| Metadata | JSON | Detailed voice list including gender, locale, and neural status. |
Edge-TTS Skill Advanced Features
- Multi-language support covering major global regions (e.g., en-US, zh-CN, fr-FR, ja-JP).
- Advanced prosody control allowing for percentage-based adjustments to pitch, rate, and volume.
- Support for multiple output qualities ranging from 24khz mono for voice notes to 48khz stereo for professional use.
- Integrated configuration manager for setting global defaults across all Openclaw Skills sessions.
- Word-level subtitle generation enabling the development of synchronized read-along applications.
SKILL.md
Loading
Related Openclaw Skills
Weiqi Player Information Query
A powerful tool to query professional and amateur Weiqi player ratings, ranks, and match history across multiple major platforms.
Creator Feed Watch
An AI-powered YouTube assistant that provides instant video breakdowns and tracks your favorite creators for new upload notifications.
Code Review Assistant
An automated code analysis tool that provides detailed review comments, performance optimizations, and security vulnerability detection across multiple programming languages.
Scar Code Review
A self-improving code review system that uses a reflex arc to prevent repeat mistakes by learning from past missed bugs.
Abyssale
The Abyssale skill empowers AI agents to automate high-volume marketing visual production and creative workflows through the Membrane framework.
Video Converter
A high-performance media transcoding tool designed to transform incompatible video files into optimized, platform-ready delivery formats.
Featured*
