Tldw
Too Long, Didn't Watch: End-to-End Rolling Summarizer of Long Videos
Install / Use
/learn @the-crypt-keeper/TldwREADME
Too Long, Didnt Watch
YouTube contains an incredible amount of knowledge, much of which is locked inside multi-hour videos. Let's extract and summarize with AI!
-
diarize.py- download, transrcibe and diarize audio- yt-dlp - download audio tracks of youtube videos
- ffmpeg - decompress audio
- faster_whisper - speech to text
- pyannote - diarization
-
chunker.py- break text into parts and prepare each part for LLM summarization -
roller-*.py- rolling summarization- can-ai-code - interview executors to run LLM inference
-
compare.py- prepare LLM outputs for webapp -
compare-app.py- summary viewer webapp
This project is under active development and is not ready for production use.
Related Skills
qqbot-channel
346.8kQQ 频道管理技能。查询频道列表、子频道、成员、发帖、公告、日程等操作。使用 qqbot_channel_api 工具代理 QQ 开放平台 HTTP 接口，自动处理 Token 鉴权。当用户需要查看频道、管理子频道、查询成员、发布帖子/公告/日程时使用。
docs-writer
100.1k`docs-writer` skill instructions As an expert technical writer and editor for the Gemini CLI project, you produce accurate, clear, and consistent documentation. When asked to write, edit, or revie
model-usage
346.8kUse CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
Design
Campus Second-Hand Trading Platform \- General Design Document (v5.0 \- React Architecture \- Complete Final Version)1\. System Overall Design 1.1. Project Overview This project aims t
