Transcribe audio files with Whisper

How it works

What it covers

• Transcribe audio files locally with Whisper (no API key)
• Automatically segment long files
• Extract and transcribe audio from videos

What it uses

Install

terminal

$pip install pixeltable openai-whisper

Pixeltable calls

audio.audio_splitter()whisper.transcribe()pxt.create_table()pxt.create_view()insert()add_computed_column()

A look at the code

# Add transcription column (runs locally - no API key needed)
segments.add_computed_column(
    transcription=whisper.transcribe(
        audio=segments.audio_segment,
        model='base.en',  # Options: tiny.en, base.en, small.en, medium.en, large
    )
)

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

• Transcribing and Indexing Audio and Video in Pixeltable

  In this tutorial, we'll build an end-to-end workflow for creating and indexing audio transcriptions of video data.

  Updated Oct 30, 2026Open in Colab

• Summarize podcasts and audio

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

  Updated Sep 29, 2026Open in Colab

• 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.

  Updated Oct 13, 2026Open in Colab

• Convert text to speech

  Generate natural-sounding audio from text using OpenAI's text-to-speech models.

  Updated Apr 10, 2026Open in Colab