edge-tts
0Generate high-quality text-to-speech audio using Microsoft Edge's neural TTS service. Ideal for developers and users needing audio output for accessibility or multitasking.
147180Updated Yesterday
Text-to-Speech
Quick InstallView Source
$ npx skills add https://github.com/aahl/skills --skill edge-ttsOverview
About This Skill
Edge TTS is a text-to-speech skill that leverages Microsoft Edge's neural TTS service to convert written text into high-quality audio. It works through the uvx edge-tts command, making it easy to integrate speech synthesis into AI workflows. The skill supports various voices and languages available through Microsoft's neural engine, making it suitable for accessibility features, content narration, and audio output generation. Developers and users can use Edge TTS to create audio files for multitasking scenarios, accessibility compliance, or automated voice generation without requiring API keys or complex authentication.
How to Use
Install using the command `npx skills add https://github.com/aahl/skills --skill edge-tts` and run via `uvx edge-tts`.
Use Cases
Generate MP3 audio files from text inputs
Produce WebVTT subtitles along with audio
Adjust speech rate, pitch, and volume for customized audio output
Facilitate audio output for accessibility features
Tags
Setup & Installation
Quick Install
Terminal
$ npx skills add https://github.com/aahl/skills --skill edge-ttsAlternative Install (Git Clone)
git clone https://github.com/aahl/skillsRequirements
- Claude Code or compatible AI agent
Quick Start Guide
1
Install the Skill
Copy the install command above and run it in your terminal.
2
Open Your AI Agent
Launch Claude Code, Cursor, or your preferred AI coding agent.
3
Try It Out
Use the prompt template or examples below to test the skill.
4
Customize
Adapt the skill to your specific use case and workflow.
Usage Examples
Prompt Template
Generate a high-quality audio file using Edge TTS for the following text: '[TEXT]'. Use the voice '[VOICE_NAME]' and set the output format to '[FORMAT]' (e.g., mp3, wav). Ensure the audio is clear and natural-sounding. Include the command to save the file as '[FILE_NAME].[FORMAT]'.
Example Output
Here’s how you can generate the audio file using Edge TTS: ```bash edge-tts --text "Hello, this is a test of Edge TTS. Welcome to [COMPANY], where innovation meets accessibility." --voice en-US-AriaNeural --rate 0% --volume 0% --output test_audio.mp3 ``` ### Key Details: - **Voice Used:** `en-US-AriaNeural` (Natural-sounding, neural TTS) - **Rate:** `0%` (Default speed; adjust with `+50%` or `-50%` as needed) - **Volume:** `0%` (Default volume; increase with `+10%` if needed) - **Output File:** `test_audio.mp3` (Saved in the current directory) ### Expected Output: A clear, natural-sounding audio file (MP3) with the provided text spoken in a friendly, professional tone. Ideal for accessibility features, podcasts, or multitasking workflows. ### Notes: - Replace `[COMPANY]` with your organization’s name. - For faster speech, use `--rate +50%`. For slower, use `--rate -50%`. - To list available voices, run: `edge-tts --list-voices`.
Find the right skills for your stack
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan