Create songs just by humming? YouTube testing GenAI tools to help create music tracks from text prompts, hum

YouTube, owned by Google, announced its testing of new generative AI features on Thursday. These features will enable individuals to create music tracks using only a text prompt or a simple hummed tune. The platform introduced Dream Track, an experiment within YouTube Shorts powered by Google DeepMind’s latest advanced music generation model, Lyria.

Lyor Cohen, YouTube’s global head of music, stated, “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.”

Nine artists, including Alec Benjamin, Charlie Puth, Charli XCX, Demi Lovato, John Legend, Papoose, Sia, T-Pain, and Troye Sivan, have opted to collaborate in this experiment. They will work alongside YouTube in shaping the future of AI in music.

YouTube is also trialling AI tools capable of generating 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,” the company explained.

Imagine effortlessly transforming thoughts and ideas into music: creating a new guitar riff by simply humming it or giving a pop track a reggaeton vibe.

“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 stated.

Meanwhile, YouTube is rolling out new rules for AI content, including a requirement that creators reveal whether they've used generative artificial intelligence to make realistic-looking videos.

Meanwhile, in a blog post published on Tuesday outlining several AI-related policy updates, YouTube announced that creators who fail to disclose their use of AI tools to create "altered or synthetic" videos may face penalties. These penalties could include content removal or suspension from the platform's revenue-sharing program.

These new restrictions build upon rules introduced by YouTube's parent company, Google, in September. The rules mandate that political ads using artificial intelligence on YouTube and other Google platforms must carry a prominent warning label.

Also Read YouTube’s new rule to tackle deepfakes and misinformation: Creators must flag altered or AI-generated content