A high-quality neural text-to-speech engine leveraging Microsoft Edge's service to provide realistic voice synthesis without an API key.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install edge-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 edge-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 Edge-TTS Skill?
The Edge-TTS skill is a powerful utility for Openclaw Skills that enables AI agents to generate natural-sounding audio from text. By utilizing the node-edge-tts library, it provides access to Microsoft Edge's neural voice service, offering a wide range of voices, languages, and fine-tuned control over prosody like speed and pitch.
This skill is designed for developers who need to add vocal capabilities to their agents without the overhead of paid API subscriptions. It supports everything from simple voice notifications to complex multi-language content generation with synchronized subtitles, making it a cornerstone for accessible and hands-free AI interactions.
Edge-TTS Skill Use Cases
- Creating eyes-free experiences where an agent reads search results or summaries out loud.
- Providing accessibility support for users with visual impairments or reading difficulties.
- Generating automated voiceovers for multimedia content with word-level timing via JSON subtitles.
- Building localized bots that can speak in dozens of different regional dialects and languages.
- Enhancing multitasking by allowing users to listen to AI responses while driving or cooking.
How Edge-TTS Skill Works
- The agent detects a text-to-speech intent through the tts trigger or a direct user request within the Openclaw Skills environment.
- The skill filters out trigger keywords (like tts or text-to-speech) from the input to ensure only the relevant content is spoken.
- Based on user preferences or default settings, the system selects a neural voice, speed, and pitch.
- The tts-converter.js script sends the request to the Microsoft Edge TTS service to synthesize the MP3 audio.
- The skill returns a MEDIA: path pointing to the generated audio file, which the agent then provides to the user for playback.
Edge-TTS Skill Setup
To integrate this skill into your library of Openclaw Skills, navigate to the scripts directory and install the required Node.js dependencies:
cd scripts
npm install
You can verify the installation by running the built-in test script to generate a sample audio file:
npm test
Edge-TTS Skill Data Schema & Taxonomy
The Edge-TTS skill manages its data through configuration files and temporary storage. The organization is structured as follows:
| Component | Format | Description |
|---|---|---|
| User Config | JSON | Persistent settings like default voice and rate stored in ~/.tts-config.json |
| Audio Output | MP3 | Temporary audio files generated in the system temp directory |
| Subtitles | JSON | Word-level timing metadata generated when the subtitle flag is used |
| Voice List | CLI Output | A real-time list of available neural voices and language codes |
Edge-TTS Skill Advanced Features
- Synchronized subtitle generation providing word-level timing for precise audio-visual alignment.
- Extensive prosody control allowing for adjustments in pitch, volume, and rate (from slow narration to rapid summaries).
- Persistent configuration management via config-manager.js to set global defaults across all Openclaw Skills.
- Support for neural voices which offer significantly higher quality and human-like inflection compared to standard TTS.
- Proxy support and customizable timeout settings for robust performance in various network environments.
SKILL.md
Loading
Related Openclaw Skills
OpenClaw Chrome Relay Helper - Mac
A specialized macOS tool to reliably attach the OpenClaw Browser Relay extension to Chrome for seamless browser automation.
aelf Skills Hub
A meta-skill hub for discovering, installing, and routing all AI agent capabilities within the aelf blockchain ecosystem.
News Digest
An intelligent, multi-slot news aggregation system that delivers personalized, AI-summarized briefings based on your specific interests and schedule.
Polymarket AutoTrader
An automated trading bot for Polymarket that uses technical analysis to trade crypto price prediction markets.
OpenFishy Feed Publisher
A powerful automation tool for generating high-quality AI visual media and publishing it directly to the OpenFishy feed platform.
Domainion Ops
A unified interface for automating domain registration, DNS records, and nameserver management across multiple providers.
METADATA
Featured*
