Google DeepMind, the artificial intelligence (AI) research division of Alphabet, has merged the Google Brain and DeepMind teams and unveiled its most advanced music generation model called Lyria.
Developed in collaboration with YouTube, Lyria is capable of generating high-quality music with both instrumentals and vocals simultaneously, offering users nuanced control over the output’s style and performance.
Google DeepMind also introduced two AI experiments: Dream Track and Music AI tools. Dream Track is a YouTube Shorts experiment designed to enhance connections between artists, creators, and fans through music creation.
Participating artists, including Alec Benjamin, Charlie Puth, Demi Lovato, Sia, and others, are testing Lyria in Dream Track. Users can input a topic and select an artist from the carousel to generate a 30-second soundtrack for their YouTube Short.
The generated content will be watermarked using the SynthID tool, which Google launched earlier this year to add a digital watermark in the form of a visual spectrogram to AI-generated audio. This measure aims to help users discern when AI-generated content is being presented as real and protect copyright.
The Music AI tools introduced by Google DeepMind are designed in collaboration with artists, songwriters, and producers to enhance their creative processes.
