The talking-head style video, will add, delete or edit the speaker's words as naturally as you'd edit the text in a word processor. A new deep fake algorithm can process the audio and video into a new file in which the speaker says whatever you want them to.
The technology would be used to cut down on expensive re-shoots when an actor muffs their lines or the script needs to be changed.
To learn the face movements of a speaker, the algorithm requires about 40 minutes of training video, and a transcript of what's being said, so it's not something that can be thrown onto a short video snippet and run if you want good results. That 40 minutes of video gives the algorithm the chance to work out exactly what face shapes the subject is making for each phonetic syllable in the original script.
From there, once you edit the script, the algorithm can then create a 3D model of the face making the new shapes required. And from there, a machine learning technique called Neural Rendering can paint the 3D model over with photo-realistic textures to make it look indistinguishable from the real thing.
Software such as VoCo can be used if you wish to generate the speaker's audio as well as video, and it takes the same approach, by breaking down a heap of training audio into phonemes and then using that dataset to generate new words in a familiar voice.
Of course, this could be used completely unethically. It will allow dishonest public figures to deny or cast doubt on genuine videos that show them in a bad light. It will also enable extremist or conspiracy theorists to create videos of people saying things which fit their agenda. A video of George Soros could be doctored to look like he operated according to the Protocols of Zion. An image of me could be used to hawk iPhones.
The research team behind this software makes some feeble attempts to deal with its potential misuse, proffering a solution in which anyone who uses the software can optionally watermark it as a fake and provide "a full ledger of edits". Yeah that will do it.