Why this matters for your business: These models deliver structural coherence, including vocals, timed lyrics, and full instrumental arrangements. You can build studio-quality audio production directly into your apps. With Lyria 3 models, you can create:
-
Multi-modal input: Generate audio using standard text prompts or by using reference images to guide the story, mood and style.
-
Vocal & lyrics: Generate vocals and timed lyrics, or use user-provided lyrics to guide the track. Need a pure soundbed? Write instrumental in the prompt.
-
Flexible compositions: Utilize duration controls to generate full songs with distinct intros, verses, choruses, and bridges.
Where you can access Lyria: Access the models via the Vertex AI API and Vertex AI Media Studio.
How Lyria 3 models are helping customers bring their audio experiences to life
“Artlist is built on profound music expertise and a commitment to setting the global sound trends that shape the digital world. Our extensive experience allows us to utilize Lyria 3 at its highest potential – combining our ‘human-in-the-loop’ musicology with Google’s most advanced generative music model to date. Lyria 3 provides an unprecedented level of creative control and high-fidelity output, resulting in a powerful fusion of technical innovation and the authentic sound that defines the Artlist brand.” – Roee Peled, Chief Product and Technology Officer, Artlist
“With Lyria 3, we’re seeing a clear shift from pure generation to true creative control — enabling Freepik’s clients to produce music that aligns more precisely with their vision and workflows. What stands out in Lyria 3 is the level of control it brings — reducing iteration time and making music generation far more predictable and usable in real-world creative pipelines” – Carlos Perez, Engineering Lead, Freepik
