Neat project. Too bad it only handles English phonemes, as it would be very valuable for teaching other languages. Maybe someday I'll convert it from ARPABET to IPA...
That's one of the reasons I made it open source - you can point your agent to it and adapt it to any other language. You'll need to record the phonemes yourself through, haven't found any AI model that can do it well.
I was thinking this too.
Especially if it handles UNICODE character sets.