Lectures → flashcards & quizzes
Rewatching a lecture feels productive and is the least effective way to revise. Testing yourself works better, and a transcript gives an AI exactly what was taught, so the questions match the lecture instead of the internet.
What you get
- 20 to 40 flashcards in question/answer form
- A 10-question multiple-choice quiz with the answer key
- A [m:ss] timestamp on every card so you can rewatch only what you got wrong
With an AI assistant
Connect the MCP server to Claude, ChatGPT or Cursor, then paste:
With the API
Set GYT_API_KEY to a key from the developers page. Each transcript, list page or channel check costs one credit.
1. Get the lecture with per-line timestamps
curl -s -H "Authorization: Bearer $GYT_API_KEY" \ "https://getyoutubetranscript.com/api/v1/transcript?v=HtSuA80QTyo×tamps=true"
Limits to know
- Questions are only as good as the captions; skim the cards for misheard terms.
Tools for this workflow
Questions
Can I import the cards into Anki?
Ask for the flashcards as CSV with front and back columns, then use Anki's File, Import. Quizlet accepts the same two columns.
Does it work for non-English lectures?
Yes, if the video has captions in that language. Pass language=xx to the API or ask the assistant for that caption language.























































