A free, high-quality text-to-speech solution that leverages Microsoft Edge's online services to generate audio without requiring API keys.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install microsoft-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 microsoft-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 Microsoft Edge TTS?
Microsoft Edge TTS is a powerful utility designed to bridge the gap between text content and high-fidelity audio synthesis. By utilizing the official but publicly accessible Microsoft Edge online TTS service, this tool allows developers and users to generate natural-sounding speech in various languages and voices. It is a core component for those building accessible applications or automated content creation pipelines using Openclaw Skills.
Unlike traditional cloud TTS providers that require complex authentication and usage-based billing, this skill provides a direct, cost-effective way to implement speech synthesis. It supports both command-line interactions for quick tasks and programmatic module invocation for deeper integration into larger software architectures.
Microsoft Edge TTS Use Cases
- Creating automated narrations for articles and documentation.
- Generating voice-overs for video content without manual recording.
- Enhancing accessibility by providing read-aloud features for visually impaired users.
- Developing multilingual bots that can communicate in native-sounding tones.
- Prototyping audio-based interfaces within the Openclaw Skills ecosystem.
How Microsoft Edge TTS Works
- The user provides a text string and optional parameters like voice selection or speech rate.
- The skill initiates a connection to the Microsoft Edge online speech synthesis endpoint.
- The text is processed by the remote engine, which applies the requested linguistic and acoustic parameters.
- An MP3 audio stream is returned and saved to a specified local directory.
- If requested, a secondary metadata file is generated to provide precise timing for each spoken word.
Microsoft Edge TTS Setup
To get started with this skill, you can use npx for one-off commands or install it as a local dependency for your projects. Ensure you have an active internet connection to communicate with the synthesis servers.
# Basic usage with npx
npx node-edge-tts -t 'Welcome to Openclaw Skills' -f './output.mp3'
# Installation as a dependency
npm install node-edge-tts
Microsoft Edge TTS Data Schema & Taxonomy
The skill primarily manages audio data and timing metadata. The following table describes the standard output structure:
| Data Type | Format | Description |
|---|---|---|
| Speech Audio | .mp3 | The primary audio file (24khz/48kbitrate by default). |
| Timing Metadata | .json | A list of segments containing the text part, start time, and end time in milliseconds. |
| Configuration | Object | JSON-based settings for voice, pitch, and rate control. |
Microsoft Edge TTS Advanced Features
- Support for over 10 high-quality neural voices across multiple languages.
- Precision control over speaking rate, pitch, and volume for fine-tuned audio profiles.
- Automatic subtitle generation with millisecond-level accuracy for word syncing.
- Built-in proxy support for environments with restricted external network access.
- Custom output format configuration to optimize for either file size or audio quality.
SKILL.md
Loading
Related Openclaw Skills
Video Editing with Français
An AI-powered video editing tool that adds French subtitles, translates on-screen text, and renders 1080p MP4 files using cloud GPU acceleration.
Code Reviewer
An automated assistant designed to analyze code quality, identify security vulnerabilities, and provide actionable refactoring suggestions.
Continuous Learning Assistant
A technical framework enabling AI agents to perform incremental training, collect user feedback, and execute self-optimization strategies.
Docker Helper
A comprehensive Docker assistant designed to automate container management, image construction, and Dockerfile optimization.
Database Migration
Execute seamless database migrations and schema transformations with zero downtime using industry-standard ORMs and rollback strategies.
Video Editing with Japanese
A specialized AI tool for automatically adding accurate Japanese subtitles and captions to video clips using cloud-based GPU processing.
Featured*
