Yes, I get the joke. But I was protesting on another thread about this kind of sentence, a native user told me that, as a teacher, he had some students who said that they lived at home, and some in an hostel. In this case, it makes sense. (Home = mummy & daddy's home.)
But I still think it doesn't make sense outside this kind of specific contexts.
Apparently, they replaced the recording you heard. The one I got was a diphthong (like the "i" in Standard American English "like"), a single blended sound, not two distinct sounds.
That is the "reconstructed classical" pronunciation.
It's possible that since the course is, at least in principle, classical Latin, and the digraph æ is a medieval creation they didn't include it intentionally.
It's also possible that you and they are using a different character set and the system just didn't know what the character you sent was.
But it's most likely that it has simply not been added yet because every one of these words would need to be added as its own varient spelling.