edge-tts

Name: edge-tts
Availability: InStock
Author: lirrensi

Convert text into speech with edge-tts and save as MP3.

4|Updated Mar 5, 2026

Search Tags:#cli #voice #text-to-speech #tts #windows #speech-synthesis #edge-tts

Ready to run

npx skills add https://github.com/lirrensi/agent-cli-helpers --skill edge-tts-lirrensi

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: edge-tts
Source: https://github.com/lirrensi/agent-cli-helpers/tree/main/skills/edge-tts
Command: npx skills add https://github.com/lirrensi/agent-cli-helpers --skill edge-tts-lirrensi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Converts text into natural-sounding speech from the terminal, enabling automation and scripting of spoken output without heavy GUI tools.

Core Features & Use Cases

Generate speech from text using edge-tts with 400+ neural voices
List voices, filter by language/gender, and adjust rate, volume, and pitch
Save output as MP3 or playback directly from the command line for quick testing and accessibility

Quick Start

Install edge-tts via uv tool install edge-tts, then use edge-tts or edge-playback to generate speech from 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 from the command line?▼

You can convert text to speech from the command line by using edge-tts to generate natural-sounding audio. This tool processes text directly in the terminal, allowing you to save the output as an MP3 file or play it back immediately.

Can I list available neural voices and filter them by language?▼

Yes, you can list available neural voices and filter them by language or gender. The edge-tts tool provides options to display all 400+ voices and narrow them down, making it easy to find the exact voice profile needed for your speech synthesis.

Do I need to install any dependencies to use edge-tts for speech synthesis?▼

Yes, you need to install the edge-tts package before using it for speech synthesis. You can quickly install the required tool by running the command 'uv tool install edge-tts' in your terminal environment.

How can I adjust the pitch, volume, or rate of generated text-to-speech audio?▼

You can adjust the pitch, volume, and rate of generated text-to-speech audio by applying specific command-line options. These edge-tts parameters allow you to customize the neural voice output to achieve the desired pacing and tone for your text.

What is the best way to automate spoken audio output without using a GUI tool?▼

The best way to automate spoken audio output without a GUI tool is using a CLI-based text-to-speech solution like edge-tts. It enables scripting and automation of neural voice generation directly from the terminal, saving results as MP3 files for immediate accessibility.