New deepfake technology can create entirely AI generated overdubs in your own voice
At least that is what the company that came up with it hopes
Deepfake is a relatively new word which describes a technique by which, using artificial intelligence, you can make human image and video synthesis. As soon as the term surfaced, it was connected with various misuse, but also good use.
As msn.com reports, a company called Descript Podcast Studio is trying to do the latter with its new audio editing software aimed at an ever-growing number of podcast makers. The key feature in their newly redesigned software is, as noted, “the ability to easily edit an artificial intelligence-generated transcription of your audio file as if you were editing a word document. Essentially, Descript turns your audio into text, broken up by who’s speaking, and it then lets you manipulate those audio files as if you were editing on a text version of the script in a word processor. Delete a sentence or two, and Descript will automatically shorten the file to make the recording sound smooth and natural.”
Yet, the company has added a completely new and unique AI tool as its creator Andrew Mason says, ”can completely overhaul the editing process.” The tool is called Overdub and allows the user to create an artificial intelligence double that can be used “ to overdub flubbed words or phrases and can even generate entirely new sentences all on its own — in your voice. It relies on technology developed by a Montreal-based AI startup called Lyrebird, which Descript says it has acquired and transformed into its AI research division.”