---
title: "Summarize podcasts and audio"
description: "Transcribe audio files and generate summaries automatically using Whisper and LLMs."
url: "https://www.pixeltable.com/notebooks/audio-summarize-podcast"
updated: "2026-09-29"
---

# Summarize podcasts and audio

Transcribe audio files and generate summaries automatically using Whisper and LLMs.

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

## How it works

You create a pipeline where audio is transcribed first, then the transcript is summarized. Both steps run automatically when you insert new audio files.

## What it covers

- Transcribe audio with Whisper (runs locally)
- Generate summaries with an LLM
- Chain transcription → summarization automatically

## What it uses

- **Install:** `pip install pixeltable openai-whisper openai`
- **Environment variables it names:** `OPENAI_API_KEY`
- **Pixeltable calls:** `whisper.transcribe()`, `openai.chat_completions()`, `pxt.create_table()`, `add_computed_column()`, `insert()`

## A look at the code

```python
# Step 1: Transcribe with local Whisper (uses GPU if available)
podcasts.add_computed_column(
    transcription=whisper.transcribe(podcasts.audio, model='base.en')
)
```

## Open it

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