Imitation is often said to be the sincerest form of flattery, but it’s hard to believe that technologies like Lyrebird won’t be used malignantly. The voice imitation AI claims to require a vocal sample of just one minute, to “compress the voice’s DNA into a unique key” that can be used to generate anything after.
By making the software available to anyone, the Montreal-based company hopes to raise awareness that such technologies exist, and eventually “raise attention about the lack of evidence that audio recordings may represent in the near future.”
This post Video: Why a voice imitation AI startup made its tech public appeared first on Tech in Asia.