
Edge Tts
This wraps Microsoft Edge's neural TTS service so you can generate spoken audio directly from Claude conversations. It's genuinely useful when you need AI responses read aloud for accessibility, multitasking, or just preference. You get a solid range of voices across English, Chinese, and French, plus control over speed, pitch, and volume. The voice quality is neural network based, so it sounds natural enough for actual use. Works through uvx, keeps it simple with direct command line calls, and can output subtitles alongside the audio files. Good for prototyping voice interfaces or making AI interactions more accessible without dealing with API keys or rate limits.
- skills.sh installs
- 203
- last updated
- Aug 21, 2026
Install
$ npx -y skills add vaibhav0806/trying-something --skill edge-tts --agent claude-codeInstalls into .claude/skills of the current project.
Files
Edge-TTS
Generate high-quality text-to-speech audio using Microsoft Edge's neural TTS service via the uvx edge-tts command.
Supports multiple languages, voices, adjustable speed/pitch, and subtitle generation.
Usage
uvx edge-tts --text "{msg}" --write-media {tempdir}/{filename}.mp3
# With subtitles
uvx edge-tts --text "{msg}" --write-media {tempdir}/{filename}.mp3 --write-subtitles -
Changing rate(speed), volume and pitch
uvx edge-tts --text "{msg}" --write-media {tempdir}/{filename}.mp3 --rate=+50%
uvx edge-tts --text "{msg}" --write-media {tempdir}/{filename}.mp3 --volume=+50% --pitch=-50Hz
Changing the voice
uvx edge-tts --text "{msg}" --write-media {tempdir}/{filename}.mp3 --voice zh-CN-XiaoxiaoNeural
Sponsors
Details
- Repository
- github.com/vaibhav0806/trying-something
- Categories
- Backend & APIs, Code Review & Quality, Marketing & SEO, Design & UI/UX, Generative Media
- First seen
- Jun 3, 2026