podcast-generator

Generate podcast audio from text by providing written content or a topic, which creates a structured script and uses ElevenLabs text-to-speech to produce the audio file. It supports solo, duo, and interview formats.

Yes, you can create an interview style podcast script from a research paper. The skill transforms research into conversational scripts featuring host and guest dynamics, explaining key findings for a general audience.

Yes, an ElevenLabs API key is required to convert text to a podcast. The skill depends on ElevenLabs for text-to-speech audio generation, alongside specific Python libraries like pydub and ffmpeg-normalize for processing.

Supported podcast formats include solo, duo, and interview styles. Generating scripts from topics produces detailed conversational structures with host and guest dynamics, allowing flexible audio production from research or written content.

The best way to normalize podcast audio after text-to-speech generation is using the skill's integrated ffmpeg-normalize dependency. It handles audio processing internally to ensure consistent sound levels across the generated podcast.

Podcast audio generation fails with missing Python libraries because the skill requires specific dependencies. You must install pydub and ffmpeg-normalize alongside configuring your ElevenLabs API key for the text-to-speech workflow to function correctly.