It is without doubt very impressive, but on longer texts the lack of understanding will be apparent. Wrong semantic stresses, incorrect pronunciation of homographs, maybe inconsistent pronunciation of names, and so on.

Perfect speech synthesis from unannotated text will require much more complex system. It will need database of common knowledge in some form, ability to relate text to that database, ability to retain and use this semantic information to guide synthesis. That is, it should be a step closer to artificial general intelligence.