I was really blown away by the voice when I first heard it... but as time went by, it started to sound like someone was reading from a book...

I can't explain it precisely, but there's a lack of "personality", made more apparent when switching from a human voice.

Very impressive stuff still.

Thanks for sharing this. The voice interaction is indeed very impressive.

I played with Meta’s SeamlessMT4 recently and I thought the output voice was quite ok for long inputs (whether text or speech). This is infitely better.

I think it is a big loss they don't get Scarlett Johansson's voice (watch the movie Her if you don't get the reference).

One of the voices sounds just like her.

Given its place by “discourse markers”, I take that to mean “don’t use ordinal markers like ‘first’, ‘second’, and ‘third’; instead use referential discourse markers like ‘then’, ‘next’, and ‘finally’”