skills.rest
wlzh
wlzhCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

text-to-speech

Convert plain text into speech using Edge TTS with adjustable voice parameters.

598|75|Updated Jan 10, 2026
Search Tags:#text-to-speech#podcast#edge-tts#voice-synthesis#script-parsing#SSML
One-click install
npx skills add https://github.com/wlzh/skills --skill text-to-speech
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: text-to-speech
Source: https://github.com/wlzh/skills/tree/main/text-to-speech
Command: npx skills add https://github.com/wlzh/skills --skill text-to-speech

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill converts written text into natural-sounding speech, enabling quick production of podcasts, audiobooks, and video voiceovers without manual narration.

Core Features & Use Cases

  • Script-aware: automatically parses and cleans podcast scripts, removing timestamps, stage directions, and markdown to keep only readable text.
  • Flexible voices: supports 18+ Chinese voices via Edge TTS with adjustable rate, pitch, and volume.
  • Post-processing: optional integration with a voice-changer skill for vocal effects and enhancements.
  • Use Case: generate podcast narration, educational clips, or video VO from scripts with minimal effort.

Quick Start

Install edge-tts and place the skill under ~/.claude/skills/text-to-speech, then run:

  • Convert a script: python3 ~/.claude/skills/text-to-speech/scripts/text_to_speech.py script.txt
  • Use a specific voice: python3 ~/.claude/skills/text-to-speech/scripts/text_to_speech.py script.txt -v zh-CN-XiaoxiaoNeural
  • Enable post-processing: python3 ~/.claude/skills/text-to-speech/scripts/text_to_speech.py script.txt --post-process
  • List voices: python3 ~/.claude/skills/text-to-speech/scripts/text_to_speech.py --list-voices

Frequently Asked Questions about text-to-speech

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

FAQPage Schema
How do I convert a podcast script to speech using Edge TTS?▼

To convert a podcast script to speech using Edge TTS, run the Python script with your text file. The skill automatically parses scripts by removing timestamps and markdown, then synthesizes natural-sounding audio for production.

Can I use SSML to adjust voice rate and pitch for text-to-speech?▼

You can adjust voice rate, pitch, and volume for text-to-speech synthesis via command-line parameters. The skill supports 18+ Chinese voices through Edge TTS to customize audio output for podcasts or audiobooks.

Do I need a local Python environment to run edge-tts for voice synthesis?▼

Yes, you need a local Python environment with the edge-tts library installed to run voice synthesis. Place the skill in your local directory and execute the Python script to generate audio from text.

What is the best way to clean podcast scripts before generating audio?▼

The best way to clean podcast scripts before generating audio is using this skill's script-aware parsing. It automatically removes stage directions, timestamps, and markdown formatting, leaving only readable text for voice synthesis.

Does edge-tts support post-processing for voice changer effects?▼

Edge TTS supports optional post-processing for voice changer effects through integration with a separate voice-changer skill. Enable this by adding the post-process flag when running the text-to-speech script command.

Related Skills

Explore More Content & Communication Skills→
jaminitachijaminitachi
1

tts

Converts Markdown documents to speech audio using the TTS pipeline.

Community
Advanced
curiositechcuriositech
181

voice-audio-engineer

Generate speech with ElevenLabs and process audio to broadcast loudness standards.

Official
Advanced
fabioc-alohafabioc-aloha
1

text-to-speech

Synthesize text to speech via Microsoft Edge TTS using TypeScript WebSockets.

Community
Advanced
different-aidifferent-ai
63

eleven-labs-podcast

Generate podcast audio from text files using the ElevenLabs API.

Official
Intermediate