Re:Deepfake Voice Technology: The Good. The Bad. The Future
by dbspin on Monday February 08, 2021 @03:59AM
(#26062207)
Obviously it's subjective, but all of these demos have the 'watery' digital sound that's an immediate giveaway. By definition they're unconvincing.
Re:Deepfake Voice Technology: The Good. The Bad. The Future
by kenoph on Monday February 08, 2021 @06:36AM
(#26063235)
I am using descript for a project of mine. You can definitely still hear that they are AI-generated. But I'm sure it's not gonna take long. Couple this with SSML and it's going to be quite convincing.
I wouldn’t call the voices unconvincing. They used to have a better demo though where it would impersonate celebrities like Trump. It was very interesting to demo it.