podcast-production

Podcast production automation streamlines the entire workflow from raw audio to published episodes. This Skill handles recording setup, audio editing with FFmpeg, transcription via Whisper, show notes generation, and RSS feed creation with iTunes metadata—eliminating manual multi-tool steps and enabling repeatable templates for each episode.

Yes. Whisper-based transcription extracts speaker labels, timestamps, and chapter data from your audio. The Skill then generates show notes and resource lists automatically, creating structured SRT outputs and formatted transcripts ready for distribution alongside your episode.

Audio processing pipelines apply FFmpeg-based normalization, noise reduction, and EQ adjustments to raw recordings. The Skill chains these operations into a configurable workflow, ensuring consistent audio quality across episodes before transcription and distribution.

RSS feed generation and iTunes metadata management enable single-source distribution. The Skill creates templated RSS entries from episode metadata, handling feed structure and platform requirements so you publish once and reach major podcast directories automatically.

The Skill uses Python-based processing with templated, configurable workflows, so you define inputs and outputs without writing code. However, familiarity with audio formats, RSS structure, and basic command-line tools helps you customize pipelines and troubleshoot workflows.