According to Microsoft, a new AI named VALL-E can impersonate your voice with just 3 seconds of audio and can also match the speaker’s “emotional range” and tempo, making it a highly accurate type of mimicry.
Thanks to a disturbing new AI named VALL-E, your voice might be digitally cloned and used to impersonate you.
With just three seconds of audio, an artificial intelligence system has been developed that can replicate any human voice.
Then, it may be used to convert any written text into speech, allowing someone to utilize the tool to talk for you.
It’s also intended to match the speaker’s “emotional range” and tempo, making it a highly accurate type of mimicry.
Thank goodness, the public still cannot access the AI tool. According to Microsoft, the “neural codec language model” (pdf ) was trained on 60,000 hours of English-language speech.
Del, a videogame artist at Naughty Facebook, the company that made “Last of Us,” claimed that “[VALL-E] can synthesize super-high-quality text-to-speech from the same voice using a 3-second sample of real speech.
Even the sample data’s emotional range and aural surroundings can be replicated.
Del said that it might have an impact on audiobooks in the future. “At the moment, VALL-E can only read, not necessarily PERFORM with the emotional, tonal and pacing range of a voice actor. However, much of the audiobook industry relies on a lot of junior voice actor talent that will undoubtedly feel the brunt of this first.”
VALL-E has undoubtedly raised some eyebrows online. “This is terrifying thinking about scam callers getting their hands on this,” tweeted Kevin Nash.
Christina Kraus, another user, wrote: “What use does this even have except for scam and impersonation purposes? Why don’t we focus on AI where it actually helps humanity? Why are we getting AI image generators and voice imitation? That’s literally the last thing we need.”
However, the tool may be extremely helpful in a variety of situations. In order to keep communicating with the outside world, people who lose their capacity to speak—like the late Stephen Hawking, who was unable to speak due to Motor Neurone Disease—could use the AI system to recreate replicas of their own voices.