A fantastic enhancement would be to allow any voice to be used in the Text to Speech, given a sample of the voice. I know Adobe demo'd VoCo a few years back and LyreBird and others are offering commercial services for this but most are not affordable or flexible enough for an Indie or Amateur.

However I noticed this article:
You can now speak using someone else’s voice with Deep Learning
https://towardsdatascience.com/you-can-now-speak-using-someone-elses-voice-with-deep-learning-8be24368fa2b

Which has a python based approach using available AI libraries/APIs that are out there and could offer a way for Indies to have better voices available without having to play with voice morphing software.

Could this be a useful addition/enhancement for iClone and Cartoon Animator?