Microsoft unveils AI tool that can mimic any voice using 3-second audio

Microsoft has unveiled an AI tool called 'VALL-E' that can closely replicate a person's voice from a three-second audio sample. According to a research paper by the company, the tool is also capable of imitating the speaker's emotional tone and acoustic environment of the sample audio. However, the paper noted that tool can be potentially misused for things like impersonation.