podcast-publishing-assistant

Transcribe long-form audio and generate publishing assets with chapter markers.

154|9|Updated Mar 27, 2026
One-click install
npx skills add https://github.com/swyxio/skills --skill podcast-publishing-assistant
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: podcast-publishing-assistant
Source: https://github.com/swyxio/skills/tree/main/podcast-publishing-assistant
Command: npx skills add https://github.com/swyxio/skills --skill podcast-publishing-assistant

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires yt-dlp, ffmpeg, whisper, and includes scripts (resource) components.

What problem does it solve?

Manually transcribing long-form audio, creating summaries, chapter markers, and all promotional assets needed to publish a podcast or interview episode is extremely time-consuming and prone to inconsistency.

Core Features & Use Cases

  • End-to-end transcription support: Handles YouTube videos, local audio/video files, podcasts, interviews, and panels, with a fallback ladder for OpenAI Whisper API and local Whisper to manage API limits and large file sizes.
  • Publishing asset generation: Produces timestamped summaries, chapter markers, YouTube titles and descriptions, X/Twitter post copy, show notes, and clip/quote card ideas.
  • Use Case: If you recorded a 2-hour panel discussion and want to publish it as a podcast episode with full YouTube metadata and social promo, this skill handles transcription, chapter creation, and all copy drafting in one workflow.

Quick Start

Use the podcast-publishing-assistant skill to turn your uploaded recorded interview audio file into a full publishing pack with transcript, chapter markers, and YouTube title options.

Frequently Asked Questions about podcast-publishing-assistant

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate podcast transcription and show notes generation?

Automate podcast transcription and show notes generation by processing long-form audio through Whisper to produce full transcripts, timestamped summaries, and ready-to-publish show notes in a single workflow.

How do I generate YouTube chapter markers from a recorded interview?

Generate YouTube chapter markers from recorded interviews by running the audio through Whisper transcription, which extracts timestamps and formats them into YouTube-compatible chapter markers automatically.

Can I use Whisper to transcribe a two-hour panel discussion with large file sizes?

Yes, you can transcribe two-hour panel discussions with large file sizes using a fallback ladder that switches between the OpenAI Whisper API and local Whisper to manage API limits effectively.

Do I need yt-dlp and ffmpeg to transcribe YouTube videos into podcast assets?

Yes, you need yt-dlp and ffmpeg to download and extract audio from YouTube videos before feeding the audio into Whisper for transcription and subsequent podcast publishing asset generation.

What is the best way to draft social copy and YouTube descriptions from a podcast episode?

The best way to draft social copy and YouTube descriptions from podcasts is using an automated workflow that transcribes the audio and generates X/Twitter post copy, titles, and descriptions simultaneously.

Does local Whisper transcription work for processing long-form video content offline?

Local Whisper transcription works for processing long-form video content offline by utilizing ffmpeg to extract the audio track first, bypassing the OpenAI Whisper API limits for large files.