A high-quality neural text-to-speech engine that converts text into natural-sounding audio using Microsoft Edge's TTS service.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install tts-1
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 tts-1 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?
The Edge-TTS skill provides a robust interface for generating high-fidelity audio from text inputs. By leveraging the node-edge-tts library, it accesses Microsoft Edge's neural voices, offering a more human-like experience than standard synthesized speech. This integration is a core component for developers looking to build accessible and interactive agents within the Openclaw Skills framework, as it requires no API keys and supports a vast library of international voices.
Beyond simple conversion, this skill allows for deep customization of the auditory output. Users can manipulate prosody elements such as speed, pitch, and volume to match the context of the content, whether it is a fast-paced news summary or a slow, clear instructional guide.
Edge-TTS Use Cases
- Creating narrated versions of text-based search results or long-form articles for hands-free consumption.
- Building accessibility features for users who prefer auditory feedback over reading text.
- Developing automated voice-over workflows for localized content in multiple languages.
- Enhancing multitasking capabilities by reading out reminders, recipes, or driving directions.
How Edge-TTS Works
- The AI agent identifies a tts intent through specific keywords or direct user commands.
- The system filters the input text to remove trigger words, ensuring only the target message is converted.
- The skill invokes the tts-converter script which connects to the neural TTS service.
- Audio is generated with specified voice parameters (language, rate, pitch) and saved as an MP3 file.
- The file path is returned as a media object, allowing the agent to deliver the audio output to the user.
Edge-TTS Setup
To get started with this skill, navigate to the scripts directory and install the required npm dependencies:
cd scripts
npm install
You can verify the installation and connectivity to the Openclaw Skills compatible service by running a basic test:
node tts-converter.js "Hello, this is a test of the text to speech system." --output test.mp3
Edge-TTS Data Schema & Taxonomy
The skill manages both configuration and temporary output data to ensure efficient operation:
| Component | Details |
|---|---|
| Configuration | Settings are stored in ~/.tts-config.json for persistent voice and rate preferences. |
| Audio Output | Files are generated in the system's temporary directory (e.g., /tmp/edge-tts-temp/) with unique timestamps. |
| Metadata | Supports JSON-formatted subtitle files with word-level timing for synchronized playback. |
| Format Options | Supports various bitrates from 24khz mono for voice notes to 48khz stereo for high-quality production. |
Edge-TTS Advanced Features
- Support for over 40 languages and hundreds of unique neural voices including Aria, Guy, and Xiaoxiao.
- Advanced prosody control allowing for precise rate and pitch adjustments (e.g., +10% speed for efficiency).
- Subtitle generation capabilities that produce JSON files with precise timing offsets for every word.
- Persistent preference management via the config-manager script to maintain a consistent brand voice across sessions.
- Proxy support and customizable request timeouts to ensure reliability in diverse network environments used by Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Transformer Core
A foundational skill that enables AI agents to understand, implement, and visualize their own underlying Transformer architecture based on the Attention Is All You Need paper.
NTM Memory System
A sophisticated external memory architecture based on Neural Turing Machines that empowers AI agents with differentiable read-write capabilities.
Memory Networks Reasoning System
A sophisticated reasoning system that integrates long-term memory components directly into the AI inference process to enable complex, fact-based decision making.
Cognitive Agent
A comprehensive framework that transforms AI into a human-like entity capable of autonomous learning, long-term memory retention, and emotional growth.
China Relocation Guide
A specialized relocation intelligence skill designed to help expats, digital nomads, and professionals navigate the complexities of moving to and living in China.
Tencent Cloud Smart Advisor Assistant
An AI-powered assistant for managing Tencent Cloud architectures, performing Well-Architected assessments, and generating secure console access links.
Featured*
