OpenAI Unveils A.I. Technology That Recreates Human Voices

First, OpenAI offered a tool that allowed people to create digital images simply by describing what they wanted to see. Then, it built similar technology that generated full-motion video like something from a Hollywood movie.

Now, it has unveiled technology that can recreate someone’s voice.

The high-profile A.I. start-up said on Friday that a small group of businesses was testing a new OpenAI system, Voice Engine, that can recreate a person’s voice from a 15-second recording. If you upload a recording of yourself and a paragraph of text, it can read the text using a synthetic voice that sounds like yours.

The text does not have to be in your native language. If you are an English speaker, for example, it can recreate your voice in Spanish, French, Chinese or many other languages.

A brief recording of a man’s voice.

Using the short recording above, OpenAI’s Voice Engine created a synthetic version of the man’s voice. Here, the A.I.-created voice reads an entirely new piece of text.

The same A.I.-created voice reads a new piece of text in Portuguese.

OpenAI Unveils A.I. Technology That Recreates Human Voices

Roidforsale.com

In a ‘Workers Economy,’ Who Really Holds the Cards?

The Fortunes of MacKenzie Scott

If war flames in Ukraine, these two little enclaves may be the spark.

Jane Campion Is Taking Cinema to the Darkest Human Places

Trudeau Wins, but Is Diminished by a Futile Election

U.K. Police Charge 3rd Man in Effort to Kill Russian Dissident

U.S., Mexico Soccer Leagues Announce an Annual Tournament

China won’t build more coal plants abroad, Xi Jinping says.

The Biden administration is combating ransomware with a crackdown on cryptocurrency payments.

Taliban Complete Interim Government, Still Without Women