---
name: podcast-chapter-generator
description: From an episode transcript, produce timestamped chapter markers with topic labels ready for Apple Podcasts and YouTube chapters.
title: Podcast Chapter Generator
category: voice-audio
difficulty: intermediate
author: admin
icon: 📻
input: text
output: structured-json
phase: post
domain: content
tags: podcast-automation,chapter-generation,topic-segmentation,embedding-distance,youtube-chapters,apple-podcasts-api,transcript-processing,audio-metadata,content-automation,llm-titling
best_for:
  - podcast production workflows
  - video content indexing
  - audience retention optimization
  - batch transcript processing
---

## 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.

## 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

1. 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.