Some further comments after playing with this a bit more:
4) The entry mechanism is going to be confusing for many people. Most people don't know how to enter a "ü" for instance. The fact that it is case sensitive is also going to be a problem. Also, the focus shifts are confusing. If you click on "I don't know," the focus is still on that button when you go to the next round, not the input field. Similarly if you click on "pause."
5) You need some way do disambiguate when there are synonyms in the vocab list.
I would largely agree with the parent's suggestions. Having an option for just the character would be especially huge, because as a native English speaker it's easy to think of the character as just a visual aid, and as such it's easily ignored.
Since you are in beta, I would find it helpful if there was a "report bugs" feature. For example, sometimes I noticed I would have something typed in correctly, but the application didn't recognize the tone marks I had (correctly) entered, which causes me to second guess myself. Or the voice recognition having trouble with certain words. I probably tried to pronounce the word for ten at least a hundred times unsuccessfully. I would expect to work at least once by accident. It would be great if I could just report this from within the app.
Other than that, I think the interface is great, and it's really FUN to use. Great job so far.
4) The entry mechanism is going to be confusing for many people. Most people don't know how to enter a "ü" for instance. The fact that it is case sensitive is also going to be a problem. Also, the focus shifts are confusing. If you click on "I don't know," the focus is still on that button when you go to the next round, not the input field. Similarly if you click on "pause."
5) You need some way do disambiguate when there are synonyms in the vocab list.