278 comments

[ 3.0 ms ] story [ 323 ms ] thread
I built a similar thing with the GPT-4 APIs a few weeks ago; thanks for the reminder that I must put it on GitHub at some point, as it's only about 30 lines of code.
I need this, but for Vimeo videos.
It should be doable. What I built only works for videos with transcripts, but I've been looking to improve it using OpenAI's Whisper for Speech-To-Text. I'm just lazy so I haven't gotten around to it (...which is why I spent an hour throwing together a 30-line script to summarize youtube videos for me)
For you or anyone else reading this I recently ran across this video documenting setting up and using whisper. It's probably a little overdetailed, but I found the github docs a little underdetailed so might be useful. Whisper is pretty powerful. One of the more useful open source ai tools available right now.

https://www.youtube.com/watch?v=XX-ET_-onYU

But as you implied in your comment, it should be possible to do it quite well with any video by transcripting with whisper and then sending the text to gpt or another LLM to summarize.

I'll check it out (or maybe let my script check it out first), thanks.

From what I remember the Whisper API docs weren't too bad, but I didn't try actually implementing anything, so you could be right that they're underdetailed.

I’m currently working on this with the caveat that I want to do the work locally. Using whisper but the summarization portion if this task is not straightforward given the limited context size of models.

Does anyone have any additional insight into this problem?

Maybe one for TikTok videos? Would be the scourge of influencers...
The GPT4 API is not generally available yet right? At least for the public?
You can apply for access, and you'll be added to a waiting list. I only have access to the GPT4 API with 8K context, not 32K.
it’s accessible via the beta. they gave me access after a day or two of waiting, but I don’t know if that’s typical or not
There's a waiting list. I applied on the first day and only just got access.
No :(. I applied several weeks ago and I still don't have access
Shouldn't it be TLDW? (Too Long, Didn't Watch)
Yes, it should. Does it matter? No, it does not.
technically it's not summarizing the video. It's summarizing the transcript of the video. So if it's a silent video with no spoken words, it likely won't do anything. So it is tl;dr of the spoken words, as parsed by Youtube ML since most videos don't have provided transcripts, though some do.
When will we get GPT that can watch video and make sense of it?
There are already many models for describing images, and Midjourney has a "/describe" feature now which takes a photo and turns it back into a text prompt. Only a matter of time until we can do video.
(comment deleted)
Wow! I love everything about this! Great product, great pricing model. I tried it out on a video I had recently watched and can confirm it works well. Giving away free summaries without even requiring a login feels very generous whereas the videos I really want to pop in are longer than the free tier allows. But the pricing still seems more than fair.

Very cool product, excited to use it more. Have you considered adding browser extension functionality? A one click button on each youtube video might be nice.

Looks useful.

Suggestion: as a non-paying user I don't immediately know what the chat tab does. You can find out under the pricing tab but it's not obvious where to find this information. Might be good to say what it does on the chat tab if you're not a paid user.

So first I tried it on a video that was too long. It produced a transcript though. Which is something. But it was an easy test. I chose an episode of a television show that is uploaded to YouTube.

So I said, "fuck it", and chose a more difficult example. A video with no talking. It's just music and images. Some algodoo/Unity physics sandbox marble competition our son likes to watch.

It just gave up.

Then I was going to try another short video with talking, but apparently you only get one summary.

So, it seems like it's a way to generate transcripts of videos and have that summarized. Neat, but not exactly what's being advertised.

Hey, at least you got one. I tried one and it said my limit was reached.
> It produced a transcript though. Which is something.

You can get those directly in YouTube, so not really something.

It's a shame; it said throttled on the first and second video I tried.

For those that don't know how:

1. Watch a Youtube video which has subtitles

2. Click the "..." button below the video, then "Show Transcript"

So many people don't know about this, it's crazy.

The tool is solid and delivers priceless value proposition for someone like me who learns by reading not by listening.

Bravo!

Tried it and immediately says I'm out of quota? Probably got hugged to death by HN?
same here.
It said I reached the daily limit on the first video I entered and didn’t even give me a summary :(
same, not a great user experience, why would I pay money when you've already shown me you fail at doing the thing?
“You've reached the daily limit of summaries allowed”
(comment deleted)
Ok, someone has to mention it: TLDW would be more precise. ;)
(comment deleted)
I’m not sure. I tried one video and got:

Something went wrong! The video could be missing subtitles for the language you selected.

So it was TLDR in my case. Almost.

TLADW actually.. (A for the ad) - great service! Now please we need a bot that posts the summary under every youtube submission.
"Summarize Tech" is a similar tool: Get a summary of any long YouTube video, like a lecture, live event or a government meeting. Powered by ChatGPT. https://www.summarize.tech/ Pros: It can summarize larger videos for free. Cons: no chat, English only, no full transcript viewer, no settings, no transcript download.
How does that handle videos longer than the token limit?
Split to smaller chunks, summarize them. Then summarize summaries.
You might want to overlap the first pass of chunks, something could get lost at the chunk boundaries. Not any sort of expert on this sort of thing, it just seems like an obvious pitfall for the context length.
I really like this idea. It’s basically applying similar principles as are used in image based nets - i.e. sliding window convolutional kernels - to text.
I built summarize.tech

Yes it's a great idea and I have a version that is basically a convolution over the transcript. It works much better than the current version - it can automatically create cohesive chapters and summaries of those chapters - however, it consumes an order of magnitude more ChatGPT API calls making it uneconomical (for now!)

Can you please eli5 the difference of old and new?
Sure. The old one just splits the transcript into 5 minute chunks and summarizes those. The reason this sucks is because each 5 minute chunk could contain multiple topics, or the same topic could be repeated across multiple chunks.

This dumb technique is actually pretty useful for a lot of people though, and has the advantages of being super easy to parallelize and requiring only 1 pass through the data.

The more advanced technique does a pass through large chunks of the transcript to create lists of chapters in each chunk. Then it combines them to a single canonical chapter list with timestamps (it usually takes a few tries for the model to get it right). Then it does a second pass through the transcript, summarizing the content for each chapter.

The end result is a lot more useful, but is way slower and more expensive.

I'm inspired that this is a side project, given everything you run. Kudos.
Thanks for the kind words. I built it on a few cross-country plane rides and now I mostly just leave it alone. The infrastructure and tooling we have these days is so incredible.
This is the standard practice already
Summary worked flawlessly on my own video.
This is way better. Than the first one. It was able to process a YouTube live video with it.
This is awesome. It described my video better than I can do it myself.
It works very well. The premium subscription is very very expensive though.
(comment deleted)
We let users build similar apps at https://trypromptly.com without writing code

When YouTube urls are used, we extract audio and transcribe it so users can either save as datasource or pass that content to other LLMs.

Ask YC (https://trypromptly.com/app/bd0a3f40-44a9-4789-b3d6-ec185134...) is an app built with content from YC startup library and some of them are YouTube videos

Excuse me sir, but why does your website have such God awful colors and contrast that I almost need therapy for my eyes after looking at it for 2 minutes?

Do feel free to hire me and have it fixed no problem. Message here if interested.

It's really restricted for free-tryout users. I'm not sure why it's so restricted though.

Seems like it might be helpful to offer a 1-5x try-out of videos up to 2 hours and then go down from there? I went straight for 1+ hour YT videos that came to mind, but was told to upgrade.

Ideally this experience could be smoothed out a bit, especially since the transcript is in some cases functionally unreadable and jarringly different from a summary.

Looks useful

There are creators that put out videos with potential but they're very bad at editing or just drag on and on about stuff.

As much as Shorts have, well, pushed for shorter videos, a lot of the longer videos need to get better at getting to the point. It doesn't have to be a short video, but think about the value you're adding by keeping something in the video instead of taking it out.

I reached the daily limit on the first video I tried to summarize.
I would like to get a sum of "Linux Full Course 11 hours" but in 666 words.
Yeah. I tried two videos. The site demanded money because it was too long. Then I tried a shorter one, and the site demanded money because I'd reached my daily limit.

Is this for real?

Where's the one that takes screenshots, I like that better
I wish there was pay for usage instead of a monthly sub.
didn't get to try - Daily Limit Reached

You've reached the daily limit of summaries allowed.

Please upgrade to Pro to continue using the service.