Microsoft’s new AI can simulate anyone’s voice with 3 seconds of audio

[Greenrex]

On Thursday, Microsoft researchers announced a new text-to-speech AI model called VALL-E that can closely simulate a person's voice when given a three-second audio sample. Once it learns a specific voice, VALL-E can synthesize audio of that person saying anything—and do it in a way that attempts to preserve the speaker's emotional tone.

Its creators speculate that VALL-E could be used for high-quality text-to-speech applications, speech editing where a recording of a person could be edited and changed from a text transcript (making them say something they originally didn't), and audio content creation when combined with other generative AI models like GPT-3.

 

https://arstechnica.com/information-technology/2023/01/microsofts-new-ai-can-simulate-anyones-voice-with-3-seconds-of-audio/?utm_source=join1440&utm_medium=email&utm_placement=newsletter

[Coffee and TV]

But will it put pronouns in its email signatures? That's the real scary part. 

[greenminer]

The next generation of fake news will include video recordings of your leader(s) making statements they did not really make.  And it will be indistinguishable from the real thing.

Get ready, y'all.

[southsideguy]

Wait until the scammers get ahold of it.

[greenminer]

11 minutes ago, southsideguy said:

Wait until the scammers get ahold of it.

oof.  I can hear it now...

"southsideguy, this is your dad.  we're going through some tough times and need to talk money..."

[UNTLifer]

Not a good idea.

[Cr1028]

Heck look at some of the deepfakes already out there with an impressionist doing the voice. It could be a double edged sword because on one hand this could be used, as several have said, to make it appear certain people have done or said things they really haven’t. On the other hand, this could be used as another “out” similar to saying your NIL’s twitter account was hacked. “I didn’t do that, they synthesized my voice” or “they deepfaked me”.

 

Edited January 13, 2023 by Cr1028