thanks for trying! May I ask what would you expect seeing and how long videos you've tried were? I saw issues on long videos liked 2hrs+, but smaller ones worked fine.

I don’t recall which videos exactly I tried it on, it was just what I had open in some tabs at the time, but they were all less than one hour.

I would have expect seeing no BS, as per your title. LLMs summaries are BS, especially when not requested. I expected that whatever your website was it would only have removed BS from YouTube (Comments? Suggested videos? I didn’t have anything too specific in mind), not added your own.

Thanks for the reply! In my understanding the no BS version would simply mean: no hellos, previews, plugs in the beginning, straight to the topic; quick summary of the whole content, regardless of the timeline; quick overview of the comments, how people reacted; the form should be not too long to have a grasp of it in a few seconds, but at the same time it should not miss key points and voice them

Would really appreciate if you could formalize your view on "no BS" version.

PS: there is definitely a bug which cuts off reply in the middle of it, will fix that.

> Would really appreciate if you could formalize your view on "no BS" version.

Only removing things, not adding anything that wasn’t there. That means no LLM summary. Pared down to the essentials, i.e. the video.

thanks, good alternative for ytdl

interesting, I was thinking about something similar. Quick bug: I can't search by the author's name?

Thank you!

Working on this side project has been both fun and rewarding. I've learned a lot throughout the process, which keeps me motivated even without immediate financial gain. I have plenty of ideas on how to improve the software in various ways. Some of these enhancements could become part of a "pro" version tailored for businesses. My long-term ambition is to turn this into a full-fledged product, which would enable me to dedicate more time to its development.

Thanks for sharing! Let me ask one quick question -- how do you host/deploy python backend (x-api)?

Since, app has selenium minimum running requirement would be 1GB RAM on any OS, and free version of any hosting do not provide that, some that provide are limited by build times or shared cpus.

So it was only logical to go through the pain/pleasure of setting up deployment on VM.

Python Backend is deployed on Azure VM(with 4 GB), since it's built on Fastapi their AWSGI support helps keep the server running on long intervals.

This one is using CF Tunnels to Prod to reduce the latency due to server location.

You can see uvicorn docs to learn more https://www.uvicorn.org/

Thanks for sharing, interesting...

interesting, thanks for sharing!