YouTube is testing GenAI tools to create music from humming and text prompts
By
siliconindia | Friday, 17 November 2023, 11:01 IST
YouTube, which is owned by Google, has announced that it is currently testing new generative AI features that will allow users to create music tracks using a text prompt or even a simple hummed tune. As part of this initiative, the company has launched an experiment called Dream Track on YouTube Shorts, which is being powered by Google DeepMind's latest and most advanced music generation model, Lyria.
"At this initial phase, the experiment is designed to help explore how the technology could be used to create deeper connections between artists and creators, and ultimately, their fans", said Lyor Cohen, global head of music at YouTube.
Nine musicians, including Alec Benjamin, Charlie Puth, Charli XCX, Demi Lovato, John Legend, Papoose, Sia, T-Pain, and Troye Sivan, have collaborated with YouTube in an experiment to shape the future of AI in music.“They are giving a small group of select US creators the chance to create unique soundtracks of up to 30 seconds for their Shorts", Cohen added.
YouTube is also experimenting with AI tools that can generate music tracks from a hum. "The artists, songwriters, and producers in the Music AI Incubator are helping us test, learn, gain feedback and hear ideas so that we can develop the best experiences possible for our community of artists, viewers and fans", said the company.
Imagine being able to more seamlessly turn one's thoughts and ideas into music, like creating a new guitar riff just by humming it or taking a pop track you are working on and giving it a reggaeton feel. "We’re developing prospective tools that could bring these possibilities to life, and Music AI Incubator participants will be able to test them out later this year", YouTube said.
Read More News :
Hewlett Packard Enterprise and Nvidia launched new solution for AI training
Paytm collaborates with Amadeus to enhance travel experiences with AI