PixeltablePixeltable Logo

Summarize podcasts and audio

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

Audio · Notebook · Updated

Open in ColabRead in the docsView on GitHub

Colab runs it in your browser. If it calls a model provider, it asks for that provider's API key in a cell.

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
terminal
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

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

One cell of the notebook, copied as it is. Open it in Colab for the rest.

More in Audio

Browse all 103