A high-fidelity text-to-speech engine leveraging Microsoft Edge's neural voices for natural-sounding audio generation.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install edge-tts-uvx
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-uvx 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-uvx?
The edge-tts-uvx skill is a robust solution for transforming written text into high-quality neural audio. By leveraging the Microsoft Edge neural TTS service through the node-edge-tts package, this skill allows users to generate lifelike speech without the need for complex API subscriptions or heavy local dependencies. It is a vital component of the Openclaw Skills ecosystem for developers looking to add voice capabilities to their agents.
This skill is particularly effective for scenarios where eyes-free interaction is required, such as accessibility tools, automated narration, or voice-enabled assistants. With support for a vast array of international voices and styles, Openclaw Skills users can customize the pitch, rate, and volume of the output to suit specific project needs, ensuring a professional and polished audio experience.
edge-tts-uvx Use Cases
- Narrating articles or chat responses for users who are driving, cooking, or multitasking.
- Providing accessibility features for visually impaired users by converting on-screen text to clear audio.
- Creating localized voiceovers for multimedia content in multiple languages and regional dialects.
- Generating synchronized subtitles alongside audio files for educational or video production purposes.
- Integrating verbal feedback into automated agent workflows via the tts trigger.
How edge-tts-uvx Works
- The user initiates a request by using the tts trigger or requesting a text-to-speech conversion.
- The system processes the input text and identifies specified parameters such as voice, rate, or pitch.
- The skill invokes the edge-tts utility through the uvx package runner to communicate with the neural TTS service.
- The service generates a high-quality audio stream which is then saved as an MP3 file to a specified directory.
- Optionally, the skill generates a subtitle file aligned with the audio timing for visual synchronization.
edge-tts-uvx Setup
To utilize this skill within the Openclaw Skills environment, you must have uvx installed. You can generate audio immediately using the following command:
uvx edge-tts --text "Your text here" --write-media ./output.mp3
To view all available neural voices supported by the skill, use:
uvx edge-tts --list-voices
edge-tts-uvx Data Schema & Taxonomy
The edge-tts-uvx skill utilizes a clear parameter-based schema to manage audio generation and metadata:
| Parameter | Description | Example Value |
|---|---|---|
--text |
The source text string to be converted | "Hello world" |
--write-media |
Destination path for the generated MP3 file | /tmp/audio.mp3 |
--voice |
The neural voice identifier for specific accents/genders | en-US-AriaNeural |
--rate |
Adjusts the playback speed of the generated audio | +50% |
--pitch |
Modifies the vocal pitch of the output | -50Hz |
--write-subtitles |
Generates a corresponding subtitle file | output.vtt |
edge-tts-uvx Advanced Features
- Synchronized subtitle generation for creating accessible video content.
- Granular control over speech prosody including volume, pitch, and speed adjustments.
- Access to a diverse library of multilingual neural voices with distinct personalities like Friendly, Positive, or Authority.
- Lightweight execution via uvx, ensuring no persistent local installation is required for individual tasks.
- Seamless integration with other Openclaw Skills to provide a multimodal user experience.
SKILL.md
Loading
Related Openclaw Skills
Audio Transcription Skill
A high-performance local audio transcription tool powered by faster-whisper for seamless speech-to-text processing.
Polygon PoS Development Skill
A comprehensive toolkit for building, testing, and deploying smart contracts on the Polygon PoS network using the Foundry framework.
LLM Wallet - Crypto & Micropayments
A specialized tool for managing crypto wallets and facilitating x402-based USDC micropayments on the Polygon network for AI agents.
x402-wach
A professional-grade DeFi safety toolkit for real-time risk scoring, honeypot detection, and liquidity analysis across major blockchains.
Home Assistant (mcp-hass)
A bridge for AI agents to interact with Home Assistant devices and states via the Model Context Protocol.
MCP Lark / FeiShu Integration
A powerful bridge connecting AI agents to the Lark and FeiShu ecosystem via the Model Context Protocol (MCP).
Featured*
