YouTube playlist → study notes

A 20-lecture course is roughly ten hours of video. As text it is an hour of reading, and you can search it, highlight it and hand it to an AI to summarise lecture by lecture.

What you get

  • One section of notes per lecture, in course order
  • Key terms with the lecture they come from
  • A one-page revision sheet for the whole course

With an AI assistant

Connect the MCP server to Claude, ChatGPT or Cursor, then paste:

List the videos in this playlist: <playlist URL>. Read the transcript of each lecture in order. For every lecture write: a 5-bullet summary, the key terms it introduces, and one question I should be able to answer afterwards. Finish with a one-page revision sheet for the whole course. Cite each point as (Lecture N, m:ss).

With the API

Set GYT_API_KEY to a key from the developers page. Each transcript or list page costs one credit; checking a channel's latest uploads is free.

  1. 1. List the playlist (1 credit per page of up to 100 videos)

    curl -s -H "Authorization: Bearer $GYT_API_KEY" \
  "https://getyoutubetranscript.com/api/v1/playlist?list=PLUl4u3cNGP61Oq3tWYp6V_F-5jb5L2iHb"

  2. 2. Get each lecture with timestamps (1 credit per video)

    curl -s -H "Authorization: Bearer $GYT_API_KEY" \
  "https://getyoutubetranscript.com/api/v1/transcript?v=HtSuA80QTyo&timestamps=true"

Limits to know

  • Captions carry speech only: equations and diagrams shown on screen are not in the text, so check the video for those.
  • Auto-generated captions can mishear technical terms; creator-written captions are more reliable.

Tools for this workflow

Playlist extractorPlaylist length calculatorYouTube to NotebookLM

Questions

How long does a whole course take?

Listing a playlist is one request per 100 videos and each transcript is one request, usually under a second. A 20-lecture course is about 21 requests.

Can I do this without code?

Yes. Connect the MCP server to Claude or ChatGPT and paste the prompt above, or open the playlist in the playlist tool and copy the transcripts out.

More workflows

EducationLectures → flashcards & quizzesTesting yourself beats rewatching. Build the questions from the transcript.MarketingCompetitor channels → weekly briefKnow what three competitors published this week without watching any of it.DevelopersPlaylist → RAG corpusIndex what a channel said, chunked on caption timings, with links that open at the right second.ContentYouTube video → blog postA post built from what was said, not a generic article on the same topic.ContentOne video → a week of postsThe best hooks are lines someone already said out loud.AutomationNew uploads → summarized alertsA free check for new videos, a credit only when there is something new.