Back to browse
ReadTube – Turn YouTube subscriptions into a personal Substack

ReadTube – Turn YouTube subscriptions into a personal Substack

by tuliren·Apr 26, 2026·2 points·0 comments

AI Analysis

MidCozySolve My Problem

Auto-fetch subscriptions beats manual URL paste but YouTube summary tools already exist.

Strengths
  • Periodic subscription fetching eliminates need to paste individual video URLs manually
  • Three summary lengths (short, long, full article) for different consumption contexts
  • Clean reading interface removes thumbnails, autoplay, and algorithmic feed distractions
Weaknesses
  • Depends on Transcript API and JustOneAPI, requires videos to have native transcripts
  • YouTube transcription and summary space has many established free and paid alternatives
Category
Target Audience

Knowledge workers, students consuming educational video content

Similar To

Eightify · Summarize.tech · Glasp

Post Description

I built ReadTube so that I can read my YouTube subscriptions.

YouTube has lots of high quality content. However, videos can be difficult to consume efficiently, especially those that are long and about series topics (e.g. general relativity, quantum physics). So I created this app to solve this need.

There are already many existing YouTube AI transcription websites. However, ReadTube is one step further in that it periodically fetches the updates from the channels I subscribe to so I don't need to paste in the video URL each time. Also it can generate two different versions of summary: one short and one long, as well as a full length article. I can pick which length to consume according to the type of videos.

Some other features: playlist import, translation, notes.

I use the Transcript API to get transcripts for YouTube videos, and JustOneAPI for Bilibili videos. These services rely on the video's native transcripts. So this app does have this one limitation that if a video has no native transcript, it won't work.

The app is built with the "standard" stack: Next.js on Vercel, Tailwind CSS, Postgres on Neon / Prisma, Clerk for auth, Gemini for summary and article generation.

I will probably open source it after I clean up the codebase more.

Similar Projects