Thank you so much both for your comment and for sharing your app! (there are definitely great tools out there that we're not aware of) I am very happy to find your app because I actually needed something like this! I enjoy listening while working and being able to see the transcription alongside it, with word definitions in context - this kind of learning really works for me! It's fantastic how it supports all those languages - you can listen, read, and look up definitions all in one place. Looking at this, the one I shared above looked very basic. You handle transcription, media playing, testing pronouncation, LLM interaction I guess for contextual meaning and examples... ! The only question I have (sorry if this already exists - but i couln't find it) but is there a chance I can see a list of words I've encountered and marked as known?

And for the second part, I'm planning to include SRS features @markvdb pointed out in comments, combining both contextual learning with SRS would be interested I guess.

I built a popular integrated reader and SRS (with Anki integration as an alternative option) similar to LingQ but focused on Japanese currently

https://reader.manabi.io

Similar to LingQ there is Migaku which can do this for YouTube and other sites. It definitely has significantly aided my learning and made it a zero friction and even fun experience to learn another language.

Thank you for sharing! Looking at their blog, I saw this post about learning Japanese vocabulary (https://migaku.com/blog/japanese/how-to-learn-japanese-vocab...). They share a Japanese Netflix Frequency List - (https://docs.google.com/spreadsheets/d/15b3j9--RJ1K5hI9vz_2L...)

"To recognize 99% of all the words in Netflix's subtitles, you'd need to know 37,247 words"

Interesting approach! I really don't know how they managed to gather this list, but it's an interesting and clever method.

You should try Lingopie.com, Its like the Netflix of Lanuguage learning. It's way more developed & Polished than Migaku or Language Reactor ... Migaku is only a chrome extension and Lingopie has thousands of TV shows and movies & also works with Netflix & Disney plus. Plus it has tons of language learning features and tools that Migaku has. You can also watch and learn on iOS & Android plus on your TV with their Smart TV apps.

There's also https://nuenki.app (disclaimer: I made it), which applies the same approach to every single website*. It translates appropriate-difficulty sentences into your target language, and you can hover for definitions, pronunciations, etc.

*other than those blocked for privacy reasons

I actually want to learn German, but I want to learn it by reading German texts and starting from zero, even though that makes it challenging. I need to look up definitions and such, but translating the entire page defeats the core purpose. This app in my case is just perfect match! Thank you for sharing!

Awesome! Let me know if you have any feedback!

Any plans to add Hindi, being the third-most spoken language in the world?

Sure, I'll add it. It isn't supported by DeepL, so it'd have higher latency (alongside a few other languages that are Claude-only).

I can contact you when it's added, if you like - perhaps you could email alex (at) nuenki.app?

That would be awesome, cheers.

I've added it.

https://nuenki.app :)

Love your work! Thanks.

I'll drop this here: If anyone wants to work on Language Reactor (well compensated), my email is in my profile. I'm planning to start open-sourcing much of it soon.

I did a double-take at the description since for a second I thought we were building the same tool. This is really cool, and seems like it'd greatly expand the set of podcasts I can listen to.

What I'm working on is different but similarly aimed at breaking through the intermediate plateau. I'm generating comprehensible input in podcast form, targeting the vocabulary used to fit a specific learning goal (e.g. "I want to be able to watch show X without subtitles") and systematically repeating the words at specific intervals to improve retention.

It works well as a prototype. I've listened to it for ~16 hours so far and it does seem to help me with vocabulary acquisition.

I'm still gauging whether I should polish and release it as a product, and would love some feedback and/or sign-ups:

https://letmeknow.jkoff.ca/infinite-ci?utm_source=hn

Wow this is super cool but how do you ensure the content is useful and correct?

To be clear, I haven't shared this with anyone because I'm not yet sure that the content is useful and correct.

As far as where I'm at: - I've listened to it in my target language for N hours. To my ear, it sounds correct and I've learned some new words that I then heard used consistently in native media. - Next, I'd like to set it to teach me a language that I already know, so that I can more reliably and easily spot errors. This will require some changes, since my target language is currently hardcoded. - Longer-term, validation based on languages I speak can't generalize 100% to other languages, nor can validation of version N make assertions about version N + 1. Correctness would benefit from native speakers periodically checking results, and usefulness would benefit from user feedback (even if only in the form of engagement or lack thereof).

Which LLM gave you the best pronunciation results?

I first generate a script to be handed to a TTS model. For this step, Claude 3.5 Sonnet works well. For voice synthesis, I've been using Google Cloud's Text-to-Speech API and it's been adequate.