Huberman Lab Podcast Transcripts

Full text transcripts of 354 episodes of the Huberman Lab Podcast, hosted by Dr. Andrew Huberman.

What's Included

Directory	Format	Description
vtt/	WebVTT (.vtt)	Original subtitle files with timestamps
transcripts/	Plain text (.txt)	Clean text without timestamps, formatted into paragraphs
episodes.csv	CSV	Episode index with titles and YouTube video IDs

Source

These transcripts are auto-generated YouTube captions, not official transcripts. They may contain:

• Inaccurate transcriptions of technical/scientific terms
• Missing punctuation or incorrect sentence breaks
• Occasional misheard words

Usage

Browse Transcripts

Each episode is available as a .txt file in the transcripts/ directory. File names match episode titles.

Programmatic Access

import csv

with open('episodes.csv') as f:
    reader = csv.DictReader(f)
    for row in reader:
        print(row['title'], row['youtube_id'])

Full-Text Search

# Search all transcripts for a topic
grep -rl "dopamine" transcripts/

# Search with context
grep -n "cold exposure" transcripts/*.txt

Use Cases

• Research and reference
• Building search indexes over podcast content
• Training data for NLP projects
• Accessibility
• Personal study and note-taking

Disclaimer

These transcripts are derived from YouTube's auto-generated captions. All content is the intellectual property of Huberman Lab. This repository is provided for educational and research purposes. If you are the content owner and would like this repository removed, please open an issue.

License

The code and tooling in this repository is released under the MIT License. The transcript content itself is subject to the original copyright of Huberman Lab.

Stats

• Episodes: 354
• Format: WebVTT + Plain Text
• Language: English