Sorry I'm lost. The sample on the homepage sounds absolutely awful. Not one bit of the cadence individually and together, the tonal ranges in responses or the overall structure and feel is comfortable to listen to, it's so far off passing as 'real' that I feel like I must be missing something.

Sure it definitely had some strange moment but it’s impressive for a small training data set and low compute

I think it sounds slightly "off" but its cadence certainly sounds way more like a human than other AI voices I've heard.

Have you tried the alternatives? This is clearly far far superior in terms of fluidity of conversation.