原始内容
Claude Skill: Podcast Generator
Generate audio podcasts from text using browser text-to-speech. Zero cost, no API keys, works in Claude.
Features
- Zero Cost: Uses browser's built-in Web Speech API (no external APIs)
- Multi-Language: Supports English, German, French, Spanish, Italian, and more
- Platform-Aware: Automatically selects best voices for iOS, Android, and Desktop
- Natural Dialogue: Converts articles, lists, or topics into engaging host-expert conversations
- Factual Accuracy: Uses source material or Claude's knowledge without hallucinations
- Interactive Player: Play/pause, resume from any line, progress tracking
- TTS-Optimized: Automatic formatting for optimal text-to-speech pronunciation
Demo
https://github.com/user-attachments/assets/497d7354-67b0-4180-b2ff-cf351c25ce3e
Installation
- Download the latest
podcast.skillfrom Releases - Open Claude (Desktop, Web, or Mobile)
- Go to Settings → Skills → "Install from file"
- Select
podcast.skill
Usage
Simply ask Claude to create a podcast:
Create a podcast about the history of artificial intelligence
Create a podcast from this article: [paste article]
Erstelle einen deutschen Podcast über Quantencomputer
Claude will automatically:
- Detect or ask for the content language
- Create a natural host-expert dialogue
- Apply TTS-friendly formatting (numbers in words, etc.)
- Generate a playable audio component
Tip: Use Microsoft Edge browser for best voice quality (250+ high-quality voices vs Chrome's 19).
What You Can Podcast
- Any Topic: Claude can create podcasts from its knowledge
- Articles: News, blog posts, documentation
- Lists: Features, events, data points
- Research: Papers, reports, summaries
- Your Own Dialogue: Pre-formatted speaker scripts
How It Works
- Analysis: Claude extracts key facts or uses its knowledge
- Dialogue: Creates host questions (~20%) and expert responses (~80%)
- TTS Formatting: Converts text to speech-friendly format
- Audio Player: Interactive component with Web Speech API
Voice Selection
Automatically detects your platform and selects optimal voices:
- Desktop Edge: Microsoft Natural voices (best quality)
- iOS/Safari: Native Siri voices
- Android/Chrome: Google TTS voices
- Desktop Chrome: Limited voices (use Edge instead)
Browser Compatibility
| Browser | Voices | Quality | Recommendation |
|---|---|---|---|
| Microsoft Edge | 250+ | Excellent | ✅ Best choice |
| Safari (iOS) | Native Siri | Excellent | ✅ Best on iOS |
| Chrome | 19 | Limited | ⚠️ Use Edge instead |
| Firefox | Very few | Poor | ❌ Not recommended |
Contributing
Contributions welcome! See CONTRIBUTING.md for:
- Development guidelines
- Skill validation
- Architecture details
- Best practices
Quick Contributions
- Additional language support
- Improved voice selection
- Better dialogue patterns
- Bug fixes
Limitations
- Requires browser with Web Speech API support
- Voice quality varies by platform and browser
- Cannot generate professional voice acting or emotions
- Works best with factual content
License
MIT License - see LICENSE for details.
Support
- Issues: GitHub Issues
- Discussions: GitHub Discussions
- Documentation: Claude Skills Docs
Built following Anthropic's skill best practices