While we've seen a lot of advancements in deepfake technology in the past few years it turns out that Microsoft just revealed a new AI tool that can simulate someone's voice in just three seconds!
Microsoft just revealed its new "neural codec language model" called VALL-E which uses AI to make text to speech synthesis sound more realistic or in other words recreate your voice with just a small sample of audio.
VALL-E is apparently capable of simulating almost anyone’s voice without them spending weeks in a studio and more often than not, VALL-E generated samples sound natural, warm, and are almost impossible to distinguish from the original speakers.
You can learn more about VALL-E HERE, but just get ready for people to use your voice wherever they want just from an Instagram story or TikTok video!
(Gizmodo)