mizorewww/course2md

Turn YouTube, Bilibili, or local course/meeting recordings into slide-illustrated Markdown and HTML lecture notes.

What it solves

It transforms video content from YouTube, Bilibili, or local files into structured, illustrated Markdown or HTML notes, eliminating the need to manually transcribe and screenshot video courses.

How it works

The tool uses a combination of video processing tools (ffmpeg and yt-dlp) and speech recognition models to convert audio to text. Users can choose between local GPU/CPU recognition (via llama-server) or cloud-based API recognition. The desktop application manages the conversion process and provides a library to organize and read the resulting notes.

Who it’s for

Students and lifelong learners who want to convert educational videos into searchable, readable study notes.

Highlights

  • Supports multiple video sources including YouTube, Bilibili, and local files.
  • Generates illustrated notes in Markdown and HTML formats.
  • Offers flexible speech recognition options: local (CPU/GPU) or cloud API.
  • Includes a desktop GUI for easy management of the conversion engine and course library.

Related

  • Project
    elder-plinius/GL4SS

    A spatiotemporal image and video engine that generates AI visuals of any location on Earth at any point in time from 252 million years ago to 3050 AD.

  • Project
    smixs/visual-skills

    A toolkit of AI agent skills that applies professional filmmaking and dramaturgy principles to generate high-precision prompts for AI video and image models.

  • Project
    MME-Benchmarks/Video-MME-v2

    A robust benchmark for evaluating video understanding in MLLMs, using a three-level progressive difficulty scale and grouped non-linear scoring to measure true temporal reasoning.

  • Project
    songlab-cal/gpn

    A suite of genomic language models designed to predict the functional effects of genome-wide variants using both aligned and unaligned genomic sequences.