podcast-generator

You can convert research material into a podcast by generating a conversational script and using text-to-speech to produce audio. This Skill automates both steps, transforming written topics into engaging audio episodes with host and guest dynamics.

Yes, an ElevenLabs API key is required to generate text-to-speech podcast audio. The Skill uses ElevenLabs for voice synthesis and Python libraries like pydub for subsequent audio processing and loudness normalization.

Automated script generation supports various podcast formats, including solo, conversational, interview, and debate styles. You can turn articles or research into a 15-minute solo explainer episode or create dynamic host and guest conversations.

Loudness normalization for generated text-to-speech audio is handled using the pydub Python library. The Skill includes specific guidelines for audio generation settings and applies loudness normalization to ensure consistent audio volume across the podcast episode.

Yes, you can generate a podcast script from a topic without producing the final audio. The Skill creates structured conversational scripts with defined guidelines before initiating the ElevenLabs text-to-speech audio generation phase.