📻

Podcast Chapter Generator

Voice & Audio · by AIDiveForge · Apr 20, 2026 · Intermediate

From an episode transcript, produce timestamped chapter markers with topic labels ready for Apple Podcasts and YouTube chapters.

🧠 Why it works

Chapter-aware listeners skip to the parts they care about, and shows with chapters have measurably higher retention on YouTube. Hand-writing chapters is tedious enough that most shows skip it. Automating the topic-segmentation step removes the cost barrier.

⚙️ How it works

Chunk the transcript into sliding windows. 2. For each boundary between chunks, compute embedding distance to quantify topic shift. 3. Apply a peak-finder to locate boundaries with high shifts AND minimum 90s spacing. 4. For each chapter, send its text to the LLM with a prompt that enforces a ≤40-char title. 5. Emit both the YouTube-formatted and Apple-API-formatted outputs plus a JSON source-of-truth.

Description

Input: a timestamped transcript (from Whisper, Deepgram, or similar). Output: chapter markers at topic boundaries with labels under 40 characters, formatted for both YouTube (MM:SS Title) and the Apple Podcasts chapter API. Chapters are spaced at least 90 seconds apart by default to avoid micro-chapters.

Install this skill

A Claude skill is a skill.md file with YAML frontmatter and a markdown body. Drop the file into your tool of choice — or pick a different format if you use Cursor, Windsurf, Copilot, or something else.

Format Download skill.md

Quick install — paste into your terminal

mkdir -p ~/.claude/skills/podcast-chapter-generator \
  && curl -L https://aidiveforge.com/skill/podcast-chapter-generator.skill-md \
       -o ~/.claude/skills/podcast-chapter-generator/skill.md

Save to ~/.claude/skills/podcast-chapter-generator/skill.md

🧠 Why it works

⚙️ How it works

Description

Install this skill

Recommended Use

Forge Auto-recommended matches

Tools

Workflow packs

Report compatibility

Suggest a pairing