AI technology continues to evolve, automating services and altering the way we interact with one another. Some forms of AI are able to mimic human speech, though the process of training an AI to learn and reproduce a human voice can usually take a while. However, the Vall-E AI voice tool has astonished audiences with how fast it can do such a thing. This particular AI voice tool can mimic a person’s speech after just a few seconds of training.
As reported by PC Gamer, Vall-E was created by a group of researchers at Microsoft. Its advantage over similar AI voice tools is that it can replicate human speech with a very small sample size. Roughly, Vall-E only needs three seconds of training in order to mimic a person’s speech. A paper was published at Cornell University (which we learned of from Windows Central) that breaks down the difference between Vall-E and other text-to-speech synthesizers.
Vall-E seems like the next major step forward for AI text-to-speech synthesizers. As AI becomes more commonplace in entertainment, communication, and art, stick with Shacknews for the most fascinating stories.