What problem does it solve?
Creating engaging podcast content from written material or topical research is time-consuming and requires scripting, voiceover, and audio production. This Skill automates the end-to-end process by converting inputs into a ready-to-publish podcast script and WAV audio. It supports both file-based inputs and topic-based web searches, and outputs two final files: podcast_script.md and podcast.wav.
Core Features & Use Cases
- From files (txt/md/docx/pdf) to a duel- or single-host podcast script and WAV audio, saving hours of manual production.
- From a user-specified topic, perform web search, synthesize information, and generate a complete podcast script and voice audio.
- Enforces duration constraints (3-20 minutes), structured dialogue, and natural pacing, with editable Markdown scripts as outputs.
- Outputs two final files: podcast_script.md and podcast.wav, with no intermediate artifacts.
Quick Start
Run the generate command with either a local material file or a search topic to produce podcast_script.md and podcast.wav.