Called VALL-E, all it needs is a three second sample of the target voice and it can generate a super-high-quality text-to-speech (TTS) example using that exact same voice.

Source: https://metro.co.uk/2023/01/11/microsofts-vall-e-ai-eerily-mimics-human-voice-after-just-3-seconds-18073230/

In January, Microsoft announced its artificial intelligence VALL-E, which could mimic a human voice perfectly after just 3 seconds.

Source: https://metro.co.uk/2023/01/31/ai-voice-generator-used-to-deepfake-celebrities-spewing-racist-abuse-18195060/

Once the AI bot learns a specific voice, VALL-E can synthesize audio of that person saying anything, and do it in a way that attempts to preserve the speaker’s emotional tone, as well as the environment where the speaker is in.

Source: https://www.firstpost.com/tech/news-analysis/microsofts-new-ai-bot-vall-e-can-replicate-anyones-voice-with-just-a-3-seconds-audio-sample-11959762.html