Guides
Transcript guides
How to pull every transcript from the channels and playlists people ask about most, and what each export format is good for.
By channel & podcast
Huberman Lab
Episodes run two to three hours, and the protocols you actually want are buried somewhere in the…
Lex Fridman Podcast
Three-hour conversations are impossible to skim. Transcripts let you find the exact exchange you…
The Joe Rogan Experience
One of the largest spoken-word archives on YouTube, and almost none of it is searchable by what was…
MKBHD
Review scripts are dense with specs and verdicts that are far easier to compare side by side as text.
TED
Talks are short and quotable, which makes the full archive genuinely useful as a text corpus.
Y Combinator
Startup advice is scattered across hundreds of talks with near-identical titles.
University lectures
A semester of lectures is a semester of watching. As text it becomes notes you can search, quote, and…
Conference talks
Conference channels dump dozens of talks at once and you only need three of them.
By export format
Markdown
Clean headings, metadata, and readable paragraphs — ready for Obsidian, Notion, or any notes app.
Plain text
Nothing but the words. The most portable format there is.
SRT subtitles
Standard subtitle file with numbered cues and timecodes, ready for any editor.
WebVTT
The web-native subtitle format, for HTML5 players and browser captions.
CSV
One row per caption segment with start time and duration — open it in a spreadsheet.
JSON
Structured segments with timestamps and full video metadata, for pipelines and code.
NotebookLM
NotebookLM takes one video at a time. This gives you the whole channel as a single source file you can…
ChatGPT
A metadata header the model can cite, then clean paragraphs — paste it in or attach it to a Project.
Claude
Long context handles an entire channel at once. This is that channel, in one file.