If you\u2019ve ever dreamed of making songs with Tupac or Jay-Z, an AI tool called Uberduck can take you close to fulfilling your fantasies.<\/p>\n\n\n\n
Uberduck<\/a> is one of a range of tools that lets you choose a celebrity voice and then enter text for them to speak. What sets it apart from the others is it can do a pretty impressive job of replicating a rapp<\/a>er\u2019s flow.<\/p>\n\n\n\n You can synthesize speech into a \u201ccalm\u201d or \u201cintense\u201d Tupac verse, for example, or try an Eminem \u201cfreestyle\u201d verse or \u201cpre-Eminem Show<\/em>\u201d flow.<\/p>\n\n\n\n Uberduck\u2019s creator says<\/a> they started working on the system with the goal of creating an open-ended dialog agent:<\/p>\n\n\n\n I built an interactive audio chatbot over WebRTC that generated text responses with a Transformer model and synthesized them to audio, but I found that speech synthesis was the most exciting part of the project.<\/p>\n<\/blockquote>\n\n\n\n The tool blew up on TikTok after a lawsuit<\/a> forced the app to swap its text-to-speech voice for a different version. Many users were unimpressed by the replacement and made the switch to Uberduck.<\/p>\n\n\n\n [Read:\u00a0Why entrepreneurship in emerging markets matters]<\/em><\/p>\n\n\n\n They\u2019ve gone on to use the tool in a range of creative ways, from adding Biggie verses<\/a> to their own tracks to making Kanye West rap the lyrics<\/a> to Bohemian Rhapsody<\/em>.<\/p>\n\n\n\n Even Linkin Park\u2019s Mike Shinoda has tried it out:<\/p>\n\n\n\n\n