cool! how did you determine the CEFR levels of the stories?

Minor, but I also see a few placeholders like "Why {{appName}}?"

I generated category levels and subcategories first. These are associated to a CEFR level and all that bundled into the story generator.

While it's currently decent for the purpose of language learning, I do need to fix consistency across longer stories because a purely sequential generation suffers from consistency in plot details.

The idea was always to offer real books in the public domian, but I decided to release it with generated stories so I could begin gather feedback on UI/UX.

Thanks for calling that out! I'll look into it.

how are users' voice recordings handled? Any guarantees about storage duration, privacy, etc.?

Voice recordings are turned to text via in-browser Speech-to-Text (STT the opposite of TTS) and then piped / sent to Grok as text. These are privately sent via my API key to Grok. I don't hold on to them at all except for sending them over the wire to Grok. So storage duration on our side is as minimal as possible, typically just a few seconds while it is sent to Grok and a reply is formulated. However, one should be aware that the whole conversation is sent to Grok from within our lesson pages, so the whole chat persists for a session until you close out the tab or move to another lesson page, at which point it is reset.

looks cool! Any thoughts on Anki interoperability (e.g., get a shared deck from ankiweb and convert to GoCard's format)?

Thanks! That is on my roadmap. I need to extract the notes form the database(sqlite)[0] from the zip file and process it along with the many media files it can contain. Right now this is a TUI and will have limited media capabilities.

[0] https://github.com/ankidroid/Anki-Android/wiki/Database-Stru...

cool! what modifications did you make to the default FSRS algorithm?

This looks cool. Are languages besides the 3 listed supported?

Thanks! Not yet, but there is no technical hurdle to add basically any language. What would you be interested in? :)

I'd be interested in french, but I guess from a business perspective spanish would make most sense.

That's probably true. I reckon I'll add both rather soon.

Chinese would be my pick

Neat idea! Does it use spaced repetition, or some other way of deciding what words to show, when?

It's rather uses unix time instead of randomness. This manner you see the same words repeatedly when you have a intermediate timer (press button every 5 minutes), it's maths.

But look instead of using space repetiton, you can just remove words you've learnt from the words list.

Thanks

looks neat! Is the quiz itself what helps with retention, or is this combined with spaced repetition or some other memory technique?

Yea! The quiz is a way to quickly review any topic days/weeks after consuming them.

I'm still figuring out the spaced repetition workflow. I'm experimenting with creating a memory database for each user after doing a quiz. For example, if you did a YC quiz and we're getting questions related to "equity" incorrect, it will take that into account when generating the next quiz.

Happy to have a chat! You could dm me on twitter: @Aayush_Mathur7 or email: aayush@studychat.app

is the XP earned constant for each item checked off, or does it vary (e.g., by difficulty or priority)?

You can choose from 5 XP, 10 XP, or 20 XP for each list item. You can also set a default XP from those 3 options so that all list items created from then on automatically reward that amount upon completion.

what makes it better than Anki? The community, email reminders, etc., or something core to the spaced repetition?

Email reminders, feedback based learning. It will tell you when to revise anything based on your learning the previous time!

ah, the "words containing" concept was pretty much how I ended up deciding to make this.

Thanks for the note and best of luck with your studying! Feel free to ping with any bugs, etc.