TL;DR: I built a web app called LangGlitch that aggregates comprehensible‑input videos (and soon podcasts/graded readers) for multiple languages, starting with German, Vietnamese, and English. I want it to become a one‑stop place for comprehensible input for every language, including small/obscure ones, and would love your feedback and language requests.
Hey folks, I’m Stefan, a guy from Germany who loves travelling and getting lost in new cultures and languages. In school I was terrible at languages and grammar never really made sense to me, but at some point I realised I had somehow become fluent in English just by playing games and watching YouTube in English.
Looking back, what worked for me was basically “comprehensible input”: content that I mostly understood and actually cared about, consumed for fun rather than as “study”. These days I always try to learn new languages that way, but I kept running into the same problem: unless you’re learning something huge like Spanish or Japanese, good comprehensible‑input content is scattered and hard to find.
So I decided to build something for myself and ended up turning it into a proper project: LangGlitch – a little web app that aggregates comprehensible‑input videos for language learners. Right now it supports German, Vietnamese, and English, with playlists grouped by difficulty, tags, and creators. You can sort for “easiest”, filter for topics you like, and then just watch your way through material instead of hunting for the next decent video.
I’d love for LangGlitch to eventually cover every language out there, including the really small and “obscure” ones, so it can be a genuine one‑stop place for comprehensible input. If there’s a language you’re passionate about and want to see added sooner rather than later, tell me in the comments or message me and I’ll do my best to prioritise it.
I’ve just put it into free open beta, so anyone can sign up and play around with it. I’m planning to add more languages over time, plus podcasts and graded readers, and if it ever makes enough money to pay its own bills I’d love to commission new comprehensible‑input content for underrepresented languages as well.
If you try it, I’d really appreciate honest feedback: confusing UI, missing features, annoying bugs, anything. You can leave comments here, DM me, or join the Discord (linked on the site) and yell at me there. Screenshots in the comments so you can get a feel for how it looks.
Always glad to hear that! Hope I didn’t come across as accusational, just kinda where my mind went trying to put on a business hat. Scary thing (maybe not for your service, but for many) is that fair-deal services have to compete with those that offer unsustainably high-value services cheap/free to get people in the door (I mean, I guess Youtube is a good example of this).
Another musing, might be nice to have videos from other sources too. PeerTube, Odysee, Vimeo, BilliBilli exist. Tiktok has some good stuff, for sure. I don’t think this is worth the trouble though, considering those first few have almost no content.
True, it would be a lot of work. Maybe, depending on your user-base, a tag only gets nominated if some # of users suggest it (say, 2+ for now). Then it goes to the suggestions queue for you to look at it. Maybe new tags, but maybe not even that, just other tags you already have that aren’t applied to any videos. I realize you already have a ‘send feedback’ thing though, so that’s probably enough right now. Also, this could involve your Discord - maybe a channel automatically gets posts sent like “Should this video have the xyz tag?” and people react thumbs up, thumbs down.
Rankings - my thinking was a few tags could maybe show under the video when browsing. Or searching by tag could return ones where the tag is most relevant.
Glad to hear the tags are human added. LLM only approach would scale better, but produce silly nonsense sometimes and make the site less fun. I do think if you have any LLM generated content (titles and description) that’s user facing, that should probably be disclosed somewhere in an About or FAQ page. For the difficulty though, that can probably use some input from automation (not even necessarily LLM, just good old fashioned code) - might not be too hard to figure out words per minute, % of common words, etc from the transcript and run time. But difficulty values from the channel that created it are probably more accurate, and I imagine most of them say what they’re targeting. And analysis wouldn’t capture things like visual aids.
I’m was thinking about this. I have to see which of these platforms allow embedding. I know TikTok does & BilliBilli doesn’t but no idea about the rest.
I like this in general. I decided against the first point because it kinda overloads the UI a bit. Maybe if I find someone who can help me with design I can revisit this. The last part sounds like something I should do. Like ordering the Videos that have the tag by relevance sounds like a decent Idea.
Well yea a pure LLM approach would be for sure faster & scale easier but you just can’t trust AI output enough so you need supervision. I actually tried to get a general sense of the difficulty based on LLM output but that took me nowhere so I had to revert back to do it manually. Most of the time I use the Difficulty the Creator has set but a lot of the times there is no difficulty anywhere & thats where I have to evaluate it myself. This is actually the hardest part because I don’t speak a lot of the languages so I’m depended on friends helping me out there.
This is actually harder than you would think. I had the same Idea after my LLM approach & it turns out this is hard as shit. Even linguists that studied a language struggle with this. Also getting data set’s for the most common words might be easy for English, Spanish, etc. but not for the more obscure/rare ones. In my research I found a service that offers this for English but it’s still mostly for written words TextInspector. Having a transcript of spoken words makes it even harder because there is no punctuation & spoken word is not always correct or uses slang. Like this whole topic is extremly complex & creating the Datasets could be a whole business by itself.
Also I added a Watch Later feature. Feel free to check it out & tell me what you think about it.
That 100% makes sense. Anything involving language seems to have potential to be a rabbit hole problem.
That was quick! Looks good. I was a little surprised to see the ‘videos like this’ sidebar when going back to watch them, instead of the playlist sidebar (since these are accessed from playlist page). But I don’t necessarily dislike that either.
Couple other things that I noticed while trying that: the ‘Superbeginner’ label feels hard to read, might need more contrast. When watching a video, the difficulty tag doesn’t seem to be anywhere. When browsing the video list, hovering over difficult expands and shows a number - but clicking still just goes to the video. When watching a video, tags aren’t clickable - I’d like to be able to click those to go to a search filtered by that tag. Creator is also not visible on the video player page, would be another good thing to be able to click.
I put the Watch Later into the Playlists for now but I’m not completely happy with that location so thats why you see the Videos like this & not the Playlist behavior. I was just unsure where to put it without disrupting the Mobile Menu.
Noted
I’ll add the Difficulty Tag!
What do you expect to happen here? The number was only meant to inform you how difficult the video is inside the Difficulty bracket (1 easiest -> 100 hardest)
How would you like this to work? Currently I save your last search settings (difficulty, Creator, Tags). So when I click on a tag should the search still use the old difficulty & creator and only use the new tag or should it clear everything and only search for the clicked tag. Same goes for creator
That’s really cool actually. I saw a sort by difficulty, so I thought there must be something more granular. But then I figured setting that level of detail for all these would be too much work.
My brain was like, this looks like a click target’, and it animating on hover doubled that impression. Following from that line of thought, I expected that the number was an amount of videos available at that difficult, maybe with some filters applied. Of course, the fact that it’s not consistent should have immediately told me I was wrong lol. What I’d expect to happen is to click there to see more [difficulty level] videos, but I don’t know that it’d be better. As always with feedback take it with a grain of salt - not pushing for changes, it’s just where one dummy got surprised.
I’m not sure how it should work, but personally I just expected to go to the search page with that tag pre-filled. Difficulty filter remembered would be better, imo. Creator, I wouldn’t be as worried about that sticking, but some people might. Might be best to keep it consistent if difficulty is saving. Maybe down the road someday, saving each of the search filters could be a setting. Mainly I just want things on the video page that I can use to find new videos. If none of the similar videos in the sidebar appeal, it can be nice to see “Oh, there’s a tag for that, maybe there are more videos about that topic”, or “Maybe I should check out all the videos from this creator”. You have that on-ramp to keep using the site.
Well you were sort of right. I didn’t set an internal difficulty for all the Videos yet. They just default to 50 if it’s not set. The Idea behind this was to use the Feedback people submit to scale the difficulty up & down because I’m 100% certain I’ll not nail all the videos on the first try.
I see. Making difficulty “persistent” makes sense because you probably wouldn’t look for a higher difficulty all of the sudden. I’ll try & see what I can up with. I’m not sure if I see saved search filters as a big feature because the last state is saved into your localStorage anyway.
Re: difficulty - Natively has a system where it asks users if x or y was harder. Like they save I’ve read this book and that book, then there’s a screen where you do that to help improve rankings. It’s kinda fun, might be something to consider if you want to make those ratings more detailed.
But then again, for mostly pretty short videos already tagged with understandable 1-5 difficulty levels, I’m not sure how important it is.
I actually like this Idea. I’m not sure if I would put that into the Feedback Dialog but having a section where a user can help to improve the Videos would be interesting.