We started indexing gobs of Youtube videos and made the world's most luxurious, diamond encrusted video search engine. The audio is stripped and digested with Deepgram (that's us—hi!). When you search, you're brought right to when people are talking about your precious little search term.

The index is 4 million+ seconds of video and growing.

I hope YouTube won't get upset with this and try to stop your project.

The search tool worked better than I expected it to. Good job on that. I read on the YC blog[1] that you're using deep learning to index audio - can you explain more about this? Do you have any experiments showing how this is better than generating a transcript of the audio?

[1] https://blog.ycombinator.com/deepgram-yc-w16-is-building-a-g...

Yep, we use deep learning to generate an index of audio features and an approximate search to look through it all. We've done lots of testing on both clear and average/noisy audio. With standard transcription matching you get ~alright results (50% retrieval) on clear audio but really terrible results on average/noisy audio (<20% retrieval). With deepgram you get great results on clear audio (90% retrieval) and still really good results (80% retrieval) on noisy/average quality content.

We're always trying to make the indexing and search better/faster. For Hoogley we had to pull some tricks to get the search to be really fast for a lot of users, so it isn't quite as high quality as it can be. Working on it though ;)

Cool stuff, good luck guys!

I like the idea (and we have the same retarded sense of humor) but it isn't consistently useful. I searched "hilary bosnia sniper fire" and got nothing.

So spend less resources on your design and more on functionality.

EDIT: Additional feedback: Your product doesn't work. If you test it yourself for a few minutes you'll see that. It is your job to test it, not the world's. You're not "getting it out there" so much as turning people away forever because they will think "I've already tried that; it didn't work". This is kinda like when my programmer employees/contractors tell me that they finished a feature but I know they never bothered to try it because it doesn't work at all.

I searched for linux and got 13 results. None of them have anything to do with linux. How is this a sexy search engine?

The sexy part refers to the looks — sorry if our sense of humor is not translating well :(

Not sure why they released, it is not even alpha product. looks like a POC

What?! You don't like click bait-y titles that point to POCs?!! You are totally right, it's a POC. <<slink away>> Just a project we put out really, really early but hope it's fun/interesting.

Indexing the entire web's videos and presenting results well is a big computational+UI problem that we are still working on. We mostly help businesses get value out of their audio/video with our API. Full scale search engine is a ways away.

It doesn't produce any useful search results for me?

Bummer. The index size is pretty small right now but we're working on increasing it right now. What were you searching for?

The voice recognition actually works very well. Obviously the results now look completely random.. To the point where it's actually funny to use

Glad you are having fun with it! That's why we put this version out. Have fun collecting flair ;P

Is Hoogley a cross between Google and Hooli?

Glad to see you guys got this on the web! I remember seeing an incarnation of this at your GTC booth.

How long did ingestion take?

Thanks! I'm glad we got __something__ to play with. This is about a day of crawling + processing.

How is this better than searching youtube auto closed captions?

It's about the same in topology — process audio, search through that, get back timestamps — but we don't rely on transcribing the words correctly.