I think there are many benign applications, and definitely a massive potential for abuse. In practice, it will be used mostly for benign applications, I think, but due to the outsized impact, you could still say the malign applications outweigh.

However, what I found reassuring is that the paper actually addresses these concerns:

"However, it is also important to note the potential for misuse of this technology, for example impersonating someone's voice without their consent. In order to address safety concerns consistent with principles such as [1], we verify that voices generated by the proposed model can easily be distinguished from real voices"

This doesn't mean it won't fool humans, especially when used in a carefully crafted setting (low-quality phone call with distressing content).