podcast-generator

To generate podcast scripts and audio, input your research topics or articles for content ingestion. The skill extracts key points, structures a narrative arc with pacing templates, and produces TTS audio via ElevenLabs for a ready-to-publish episode.

Supported podcast script formats include solo explainer, conversational duo, interview, and narrative styles. Each format provides structured episode templates with cold open, setup, segments, takeaways, and outro tailored to typical 5–40 minute episodes.

Yes, the skill relies on ElevenLabs for text-to-speech generation. It produces TTS-based audio with configurable voices and delivery settings, handling content chunking and audio normalization to deliver ready-to-publish audio assets.

Yes, you can generate a conversational duo or interview podcast script from an article. The skill ingests source materials to craft a compelling narrative arc and produces host/guest dialogue tailored to your chosen multi-host format.

Text-to-speech podcast audio generation requires content chunking for longer 5–40 minute episodes and relies on ElevenLabs voice configuration. Users must manage delivery settings and audio normalization to maintain consistent production quality.