edge-tts

Automates text-to-speech conversion using Microsoft Edge neural voices via node-edge-tts.

37|9|Updated Mar 4, 2026
One-click install
npx skills add https://github.com/yangkun19921001/PP-Claw --skill edge-tts-yangkun19921001
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: edge-tts
Source: https://github.com/yangkun19921001/PP-Claw/tree/main/skills/edge-tts
Command: npx skills add https://github.com/yangkun19921001/PP-Claw --skill edge-tts-yangkun19921001

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires node-edge-tts, commander, and includes scripts (resource) components.

What problem does it solve?

Transforms user text into natural-sounding speech using Edge's neural voices, eliminating manual voice synthesis setup and API-key requirements.

Core Features & Use Cases

  • TTS synthesis with Edge neural voices via node-edge-tts
  • Supports multiple languages and voices, with adjustable pitch, rate, and volume
  • Optional subtitles in JSON and output to MP3
  • No API key required; runs with internet access

Quick Start

Install dependencies and run the tts-converter script to synthesize speech from your text.

Frequently Asked Questions about edge-tts

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert text to speech using Node.js without an API key?

You can convert text to speech by running the Node.js tts-converter script via commander, which uses the node-edge-tts package to synthesize natural-sounding speech into an MP3 file without requiring an API key.

Can I generate multilingual TTS audio with adjustable pitch and rate?

Yes, this text-to-speech conversion supports multiple languages and voices, allowing you to configure voice parameters such as pitch, rate, and volume during MP3 audio synthesis.

Do I need an internet connection to use Edge neural voices locally?

Yes, you need internet access to run the text-to-speech synthesis. The Node.js library leverages Microsoft Edge's neural voices online, meaning an active connection is required even though no API key is needed.

Can I generate subtitles along with my text-to-speech MP3 output?

Yes, the text-to-speech script can optionally output subtitles in JSON format alongside the generated MP3 audio file, providing timestamped data for read-aloud applications.

What are the limitations of using node-edge-tts for application development?

The primary limitation of using node-edge-tts for application development is its dependency on an active internet connection to access Microsoft Edge's neural voices, as offline text-to-speech synthesis is not supported.