This is the audio equivalent of the Face2Face algorithm that takes one person's face and places it onto the character in a video, matching the latter subject's expressions. This means we now live in a world where you can create a recording of Donald Trump saying, "I colluded with the Russians to rig the election," and not only have the voice sound like Trump but also bring along his personal expressive style so that…
Also this means that any confession evidence can not be trusted.