AI

Purpose

The rate at which I save YouTube videos is always faster than the rate at which I can actually watch them. Research videos I’ve bookmarked, videos I’ve saved for later, links I copied because they might become references—they keep piling up. The bottleneck is time.

Most existing YouTube summarization tools rely on embedded subtitles, i.e., transcripts uploaded by the creator. If a video has no transcript, summarization becomes impossible. Videos without Korean subtitles, videos with low-quality auto-captions, or videos with no captions at all still require watching from start to finish.

I previously used Claude + Blender MCP for production work while I was employed at a company. Recently, as I restarted a personal project, I rebuilt the same environment—and this time, I decided to document the process.

Most reference blogs are written for Windows setups, so this post is organized from the perspective of someone actually working on macOS, in a way that designers can realistically follow.

To be honest, I’m not particularly good at 3D modeling. Even creating a single object used to take me two or three full days, and scene-level work took much longer. This approach was something I tried to compensate for those limitations and produce results more quickly.