Facilitating the Spread of Knowledge and Innovation in Professional Software Development

Write for InfoQ


Choose your language

InfoQ Homepage News Google Announces New DeepMind Model, Lyria, to Generate High-Quality Music

Google Announces New DeepMind Model, Lyria, to Generate High-Quality Music


Google has introduced Google DeepMind's Lyria, an AI music generation model able to generate vocals, lyrics, and background tracks mimicking the style of popular artists. The model is experimentally available on YouTube through two distinct AI experiments.

One of the experiments, Dream Track, aims to let creators generate short music clips using the voices and styles of collaborating artists such as Alec Benjamin, Charlie Puth, Charli XCX, Demi Lovato, John Legend, Sia, T-Pain, Troye Sivan, and Papoose.

Dream Track users can simply enter a topic and choose an artist from the carousel to generate a 30 second soundtrack for their Short. Using our Lyria model, Dream Track simultaneously generates the lyrics, backing track, and AI-generated voice in the style of the participating artist selected.

The second experiment, named Music AI tools, aims to expand the possibilities of using AI throughout the creative process.

With our music AI tools, users can create new music or instrumental sections from scratch, transform audio from one music style or instrument to another, and create instrumental and vocal accompaniments.

For example, says Google, Lyria can transform a melody you hum into a saxophone line, MIDI chords into a vocal choir, or add background instrumental music to a vocal track. Lyria also supports specifying the elements that should go into the generated piece, such as instruments, effects, and techniques, using a textual prompt.

Alongside Lyria's music generation capabilities, Google is also exploring new ways to make AI creation deployment socially responsible. Specifically, Lyria will watermark any content it generates by embedding the watermark directly into the generated waveform using SynthID. Currently in beta, SynthID is a tool for watermarking and identifying AI-generated content.

With this tool, users can embed a digital watermark directly into AI-generated images or audio they create. This watermark is imperceptible to humans, but detectable for identification.

SynthID uses two deep learning models, one for watermarking and the other for identifying. While SynthID is only the first step in the direction towards making AI artifacts traceable, in Google's view it responds to a critical need when it comes to being able to identify AI-generating content to protect against misinformation.

Lyria is still experimental and very much a work in progress. Google says that early Music AI Incubator participants will be able to test it out later this year.

About the Author

Rate this Article


Hello stranger!

You need to Register an InfoQ account or or login to post comments. But there's so much more behind being registered.

Get the most out of the InfoQ experience.

Allowed html: a,b,br,blockquote,i,li,pre,u,ul,p

Community comments

Allowed html: a,b,br,blockquote,i,li,pre,u,ul,p

Allowed html: a,b,br,blockquote,i,li,pre,u,ul,p