Yes, notation seems to be critical. I wanted to see how well it can recreate the training data; so I picked Kyle from South Park and put in "they killed Kenny". I assume this should be in the training set, being a running theme in the show. The inference puts it in a question-like tone, not like the original.
I wish there was some kind of notation to help generate intended inflection and emphasis. Like <sarcasm> or /s tags
Here is my bojack. What are youuuu doing here is read flat and funny! suck a D dumb S sounds decent though.
https://fakeyou.com/tts/result/TR:n45c3yyjwrg3fqbdcxfpn3xrac...