Google launches AI music generator Lyria 3 Pro, says it was trained on data it has the right to use

2026-03-25 · Source: The Decoder · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Emerging Technologies & Innovation · Depth: Fundamental Awareness, quick

Summary

Google has launched Lyria 3 Pro, its latest AI model designed for music generation, capable of producing tracks up to three minutes in length. This advanced model demonstrates an improved comprehension of musical structures, including intros, verses, choruses, and bridges, compared to its predecessor, Lyria 3. Lyria 3 Pro is integrated into multiple Google platforms, such as the Gemini app for subscribers, Google Vids for Workspace clients, Vertex AI for enterprises, and Google AI Studio for developers. Additionally, the collaborative music tool ProducerAI utilizes this model. Google asserts that Lyria 3 Pro uses artist names in prompts for inspiration rather than imitation and was trained on data YouTube and Google are legally entitled to use, though specific training data details remain undisclosed. All generated content is embedded with an invisible SynthID watermark.

Key takeaway

For CTOs evaluating AI music generation solutions, Lyria 3 Pro offers a robust, structurally aware model with broad integration across Google's ecosystem. Your teams can leverage its capabilities for diverse applications, from content creation in Google Vids to custom development via Vertex AI, while benefiting from Google's stated commitment to legal data usage and SynthID watermarking.

Key insights

Google's Lyria 3 Pro advances AI music generation with improved structural understanding and broad platform integration.

Principles

• AI models can learn complex musical structures.
• Watermarking AI-generated content enhances traceability.

In practice

• Generate music up to three minutes with Lyria 3 Pro.
• Utilize Lyria 3 Pro via Gemini, Vids, Vertex AI, or AI Studio.

Topics

• AI Music Generation
• Lyria 3 Pro
• Google AI
• SynthID
• AI Copyright

Best for: Investor, CTO, Executive, AI Engineer, AI Product Manager, Tech Journalist

Related on AIssential

• 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.
• 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.
• 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.
• 😺 Watch: This AI just made our podcast theme song — Google's Flow Music, powered by Lyria 3, enables iterative AI-driven music and video creation.
• Google DeepMind Releases Lyria 3: An Advanced Music Generation AI Model that Turns Photos and Text into Custom Tracks with Included Lyrics and Vocals — Lyria 3 is a multimodal AI generating high-fidelity music with vocals and lyrics from text and photos.
• Google Gemini Integrates AI Music Generation — Google's Lyria 3 model integrates AI music generation into Gemini and YouTube, offering creative tools with guardrails.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by The Decoder.