Creepy AI can clone anyone's voice

A new start-up lets users synthesise a person's speech from just a one minute-long recording of them talking. Using artificial intelligence (AI) the Lyrebird service uses a voice-imitation algorithm to mimic a person's voice and have it read any text with a given emotion. Although this voice-copying technology might be amusing it also has serious implications as users can essentially poach part of someone else's identity. The Lyrebird service synthesise a person's speech from just a one minute-long recording and can generate 1000 sentences in less than half a second (stock image) The Lyrebird service allows users to compress the individual characteristics of a voice into a single key which means users can generate 1000 sentences in less than half a second. Not only can users create voices but they can control the generated voice too - for example making it sound angry, sympathetic or stressed.