Build music generation into your apps with Lyria 3 models on Vertex AI
To meet your diverse needs, we offer two distinct models via the API:
*
Lyria 3 Pro: Generates complete compositions up to three minutes long. It understands musical architecture, allowing for specific structural elements like intros, verses, choruses, and bridges.
* Lyria 3: Generates tracks up to 30 seconds long. It’s ideal for rapid prototyping, social media assets, and short-form audio generation.
Introducing Lyria 3 Pro
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
Lyria 3 Pro on Vertex AI
Commercial safety and responsible creation
Responsibility is foundational, and remains integral in the design and training of Lyria 3 models, using materials that YouTube and Google has a right to use under our terms of service, partner agreements, and applicable law. Additionally, we employ filters to check outputs against existing content and users must adhere to the Terms of Service and Gen AI prohibited use policies, which prohibit violating others' intellectual property and privacy rights. All Lyria 3 and Lyria 3 Pro outputs are embedded with SynthID watermarking and support C2PA.
Start building today
To dive deeper into the best practices, explore the following resources:
*
Model card
*
Ultimate prompting guide for Lyria
*
Gen AI SDK for Python notebook
*
If you’re using these models with our Gen Media MCP tools, you can provide domain-specific sound design knowledge via this Agent Skill
If you're a Google Workspace customer or Google AI subscriber, you can also experience Lyria 3 models in Google Vids to give your videos a custom track that matches your brand’s style.
Create custom tracks with Lyria 3 Pro in Google Vids 🔗 Google IA
https://cloud.google.com/blog/products/ai-machine-learning/lyria-3-and-lyria-3-pro-on-vertex-ai/?utm_source=dlvr.it&utm_medium=blogger
No hay comentarios.