John Legend, Demi Lovato to Trial AI Versions of Their Voices
Artificial Intelligence (AI) is hitting the mainstream in a big way. Some of the biggest artists in music are trialing AI-generated versions of their voices for YouTube. Among these artists include John Legend, Demi Lovato, Sia, Charlie Puth, Charli XCX, T-Pain, Troye Sivan, Alec Benjamin, and Papoose. The Google-owned video platform is using a music generation model to produce 30-second clips in a limited trial for creators. YouTube says the Dream Track experiment has been opened to about 100 US creators using its Shorts feature.
In a blog post, YouTube said creators would be able to produce a 30-second soundtrack by typing a text prompt. “By simply typing an idea into the creation prompt and selecting a participating artist that appears in the carousel, an original Shorts soundtrack featuring the AI-generated voice of that artist will be produced for the creator to use in their Short,” the site reads. YouTube posted examples using an AI-generated Charlie Puth singing “a ballad about how opposites attract, upbeat acoustic.” In another example, the prompt reads: “A sunny morning in Florida, R&B” for a T-Pain tune. The voice, instrumentation, and lyrics in the Dream Track experiment are all AI-generated.
YouTube also hopes to produce AI-generated results like humming a tune and converting it into a guitar riff or taking a pop track and turning it into a reggaeton song to test later this year. According to The Guardian, the Dream Track trial is powered by Lyria. This week, YouTube said it was introducing a tool that would allow music labels and distributors to complain about unsolicited AI content that mimics an artist’s voice. It will also allow people to complain about deepfakes, although it adds that parodic content or deepfakes of public officials and well-known individuals might be kept up on the platform.