cast_otter

Seoul · since 2010Numbers first

@cast_otter

← All works Works · 04

Lecture Learning

Give it one well-made lecture video and it writes up the content, how it was made and how it was spoken, each on its own.

Running4 key · Lecture Learning

01The problem

After a good lecture, all that sticks is “that was good”. What it said, how the screen was laid out, how the speaker talked: it fades fast, and going back means watching from the top.

02How it works · 3 steps

  1. Drop it in

    The video is cut into sections on a colour-coded timeline.

  2. Read it three ways

    A content summary, how it was made (structure, visuals, editing) and the speaking craft (openings, emphasis, pace), kept apart.

  3. Keep the notes

    Study notes with a timestamp on every section, so the scene you want is easy to find again.

03Screens

The Lecture Learning job list: an input for a new video and a card for a job in progress, with the text blurred.
Real screen · data blurred
The Lecture Learning detail screen: a video player over a colour-coded section timeline, and a timestamped section list on the right, with the content blurred.
Real screen · data blurred

04Stack

  • A video-capable AI model
  • Python
  • Local web UI on a Mac
  • Built with an AI coding tool

05Status

Running

It is one of the menus inside the video studio. Lecture titles and notes are blurred.