podcast-generator

To turn research into a podcast, provide your source material or topic as input. The skill automatically ingests the content, formats it into a podcast-ready script, and produces text-to-speech audio using ElevenLabs for publication.

You can generate multiple podcast script formats from written articles, including solo explainer, conversational duo, interview style, debate, and narrative. This allows you to repurpose research content into the audio generation format that best fits your audience.

Yes, generating text-to-speech audio for podcasts requires ElevenLabs. The skill uses ElevenLabs to render dialogue from the generated script, applying voice settings and prosody guidance to produce the final audio file.

You can convert long research articles into audio by chunking the generated script. The skill provides guidance on chunking text for ElevenLabs text-to-speech processing, followed by a loudness normalization step to ensure consistent audio publication quality.

The best way to repurpose content into a conversational podcast is using an automated script writing pipeline. It converts source material into host and guest dialogue formats, then directly outputs the structured scripts into ElevenLabs audio generation.