---
title: "Generate Podcast Chapters"
description: "Generate YouTube-style chapter timestamps for podcast episodes. WhisperX detects where speech starts and stops, then an LLM summarizes each segment into a chapter title."
url: "https://www.pixeltable.com/notebooks/audio-podcast-chapters"
updated: "2026-10-13"
---

# Generate Podcast Chapters

Generate YouTube-style chapter timestamps for podcast episodes. WhisperX detects where speech starts and stops, then an LLM summarizes each segment into a chapter title.

- **Type:** Notebook
- **Group:** Audio

## What it uses

- **Install:** `pip install pixeltable whisperx openai`
- **Environment variables it names:** `OPENAI_API_KEY`
- **Pixeltable calls:** `pxt.create_table()`, `pxt.create_view()`, `@pxt.udf`, `insert()`, `add_computed_column()`

## A look at the code

```python
episodes.add_computed_column(
    transcription=pxtf.whisperx.transcribe(
        episodes.audio, model='tiny.en'
    )
)
```

## Open it

- **Open in Colab:** https://colab.research.google.com/github/pixeltable/pixeltable/blob/release/docs/release/howto/cookbooks/audio/audio-podcast-chapters.ipynb
- **Docs page:** https://docs.pixeltable.com/howto/cookbooks/audio/audio-podcast-chapters
- **Source on GitHub:** https://github.com/pixeltable/pixeltable/blob/release/docs/release/howto/cookbooks/audio/audio-podcast-chapters.ipynb