This is one of the worst use cases for AI. You have no way to verify the quality of the output. Many of these texts are going to have pronunciations that will be difficult for today’s TTS systems. Plus, many of these are already available from good voice actors, many of them free, and they do the proper service to these texts.
It seems like you did a lot of good technical work, but I find this project entirely useless and a waste of resources.
Discord isn’t the right tool for a knowledge base, but it’s great for communities. I run several servers but I wouldn’t recommend it for developer projects.
No it’s still in its infancy. I’m focusing on capturing data as seamlessly as possible but I don’t want any of it to reside in a silo. I’ve got about 15 different shortcuts right now but I think I could probably pare this down with some custom shortcuts if I can figure out how to build them into a simple app. I’ll do a write up at some point when the system bears fruit.
The problem with most habit tracking apps is that they don’t put your habits in context with the rest of the day. For example, let’s say you miss a day reading, and that becomes a pattern. Current apps may not surface the fact that you’ve taken on too many evening commitments because they can’t show you your calendar.
I’ve been using Chronicling, another iOS app by an indie dev, and it lets you track just about anything, but since you can’t get data out easily you end up having a silo of events about habits without any sense of why you may or may not be keeping habits.
So, I’m building my own activity tracking now with a grist database since they have a nice API and in the end you end up with SQLite files which are highly portable. I am integrating a bunch of iOS shortcuts and also using n8n to auto populate as much as possible into the tracker so that I can correlate habits with other daily activities.