Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More
Google DeepMind today unveiled its newest and “most advanced” music AI system yet, called Lyria. The company says the model can generate high-quality vocals, lyrics, and musical backing tracks that mimic the style of popular artists.
DeepMind announced Lyria alongside new music creation experiments launching on YouTube Shorts. One of the experiments called “Dream Track” will let creators generate 30-second songs sung in the voices of artists such as Alec Benjamin, Charlie Puth, Charli XCX, Demi Lovato, John Legend, Sia, T-Pain, Troye Sivan, and Papoose.
DeepMind claims these projects will “open a playground for creativity” and help artists connect with fans. Jim Fan, research scientist at NVIDIA AI, went one step further. He tweeted: “The most impressive demo is converting humming to a full instrument suite. I think Lyria will unlock all the operators we are used to in image models: text-based editing, style transfer, in-painting (fill out tracks), out-painting (continue a track), super-resolution, etc.”
The business score
Lyria (and other AI music tools like it) could be a game-changer for the music industry. By arming musicians with advanced tools for creation and experimentation, Google could democratize music production, allowing both established and budding artists to create without constraints.
The partnership with YouTube could redefine the way music is streamed and consumed, fostering a more immersive relationship between artists and fans. This disruption to traditional music distribution models could lead to new business opportunities and revenue streams.
Furthermore, this move reinforces Google’s position at the vanguard of AI application in creative fields, demonstrating how AI can augment creative processes beyond the realm of technology.
Striking the Chord of Responsibility
DeepMind is also setting the tone for responsible deployment of AI technologies. The company is using SynthID to watermark and identify synthetically generated content, ensuring traceability of any content produced by Lyria back to its AI source.
“As we move forward, we’ll continue engaging artists, the music industry, and the wider creative community to set the standard for the responsible development and deployment of music generation tools,” the company affirmed.
In an era fraught with debates about AI ethics and the need for transparency in AI-generated content, Google’s move to watermark its AI-generated music is a significant stride towards responsible AI deployment, setting a benchmark for the industry.
Google has thus far provided very few details around artist partnerships. For now, Lyria’s capabilities remain limited, unable to match humans’ creative originality. But its rapid progress highlights ethical and legal quandaries that must be addressed as AI generation matures, experts say.