New voice mode is a speech predicting transformer. "Voice Cloning" could be as simple as appending a sample of the voice to the context and instructing it to imitate it.
OP seems to be on the "They secretly trained on her voice" train. The only reason "Two Days!" would be damning is if a finetune was in order to replicate ScarJo's voice. In that sense, it's much better.
>(C) it's extraordinarily reckless to go from zero to big-launch feature in less than two days.
Open AI have launched nothing. There's no date for new voice mode other than, "alpha testing in the coming weeks to plus users". No-one has access to it yet.
This mode works entirely differently from what Open AI demoed a few days ago (the new voice mode) but both seem to utilize the same base sky voice. All this uproar is from the demos of new sky which sounds like old sky but is a lot more emotive, laughs, a bit flirty etc.