Lyria 3 Pro: Create longer tracks in more

2026-03-25 · Source: Google DeepMind News · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Emerging Technologies & Innovation · Depth: Intermediate, medium

Summary

Google has introduced Lyria 3 Pro, an advanced music generation model that extends track creation up to 3 minutes and offers enhanced structural awareness for elements like intros, verses, and choruses. This model, building on Lyria 3's custom music generation capabilities, is now integrated across several Google products and services. It is available in public preview on Vertex AI for businesses needing scalable audio production, in Google AI Studio and via the Gemini API for developers, and within Google Vids for custom video soundtracks. Additionally, Lyria 3 Pro is rolling out to paid subscribers of the Gemini app and is integrated into ProducerAI, a collaborative music creation tool. Google emphasizes responsible development, partnering with artists through initiatives like the Music AI Sandbox, and employs SynthID watermarking to identify AI-generated content while adhering to IP and privacy policies.

Key takeaway

For developers building creative audio tools or businesses requiring scalable music production, Lyria 3 Pro offers significant advancements in track length and structural control. You should explore its public preview on Vertex AI or integrate it via the Gemini API to leverage its enhanced compositional awareness for more complex and customized audio outputs. This update enables richer, more structured musical content for diverse applications, from gaming to video production.

Key insights

Lyria 3 Pro extends AI music generation to 3-minute tracks with structural control across Google's ecosystem.

Principles

• AI music generation should be widely accessible.
• Responsible AI development requires industry partnership.
• Protect original expression and intellectual property.

Method

Lyria 3 Pro uses advanced musical composition understanding to generate longer tracks (up to 3 minutes) with specific structural elements (intro, verse, chorus) and embeds SynthID watermarks for content identification.

In practice

• Generate bespoke soundtracks for gaming via Vertex AI.
• Integrate Lyria 3 Pro into creative tools using the Gemini API.
• Add custom music to marketing videos with Google Vids.

Topics

• Music Generation
• Lyria 3 Pro
• Generative AI
• Vertex AI
• Responsible AI

Best for: AI Engineer, Machine Learning Engineer, Product Manager, Software Engineer, Creative Technologist, AI Product Manager

Related on AIssential

• Lyria 3 Pro: Create longer tracks in more Google products — Lyria 3 Pro extends AI music generation to 3-minute tracks with structural control across Google's ecosystem.
• Build with Lyria 3, our newest music generation model — Lyria 3 offers AI music generation with structural coherence, expressive vocals, and granular control via text and multimodal inputs.
• Google Gemini Integrates AI Music Generation — Google's Lyria 3 model integrates AI music generation into Gemini and YouTube, offering creative tools with guardrails.
• Google launches AI music generator Lyria 3 Pro, says it was trained on data it has the right to use — Google's Lyria 3 Pro advances AI music generation with improved structural understanding and broad platform integration.
• Google adds AI music generation to Gemini with Lyria 3 — Google's Lyria 3 model enables AI music generation in Gemini and YouTube, featuring mood-matching and content identification.
• Record scratch—Google's Lyria 3 AI music model is coming to Gemini today — Google's Gemini app now offers AI music generation with Lyria 3, featuring SynthID watermarking and copyright considerations.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Google DeepMind News.