Vertex AI is Google’s platform for developers to build, train and test generative-AI apps. As of this week, it includes some new music features.
The tech giant announced that it has made its Lyria text-to-music model available on Vertex AI for developers to use. Lyria was originally unveiled in November 2023 by Google’s DeepMind team, and has been used by YouTube for its AI-music experiments.
Now it’s being made available more widely with a twin pitch to brands and creators.
“Quickly create soundtracks for marketing campaigns, product launches, or immersive in-store experiences, all tailored to your brand’s unique identity,” is the message to brands.
Meanwhile, for video and podcast makers its a royalty-free soundtrack pitch: “generate custom music tracks in minutes, directly aligning with your content’s mood, pacing, and narrative…”
As part of the announcement, Google offered a snapshot of what Lyria is capable of, in response to a detailed text prompt.
“Craft a high-octane bebop tune. Prioritize dizzying saxophone and trumpet solos, trading complex phrases at lightning speed. The piano should provide percussive, chordal accompaniment, with walking bass and rapid-fire drums driving the frenetic energy. The tone should be exhilarating, and intense. Capture the feeling of a late-night, smoky jazz club, showcasing virtuosity and improvisation. The listener should not be able to sit still.”
Source: Google adds Lyria text-to-music model to Vertex AI platform
