Google launches Lyria 3 Pro, extending AI music generation to 3-minute tracks

Google has released Lyria 3 Pro, a music generation model that extends track length from 30 seconds to 3 minutes and adds structural understanding of musical composition, according to an announcement on Wednesday.

The new model improves upon Lyria 3—released one month prior—by allowing users to specify discrete musical elements in prompts, including intros, verses, choruses, and bridges. Google claims the model demonstrates improved understanding of track structure compared to its predecessor.

Availability and Integration

Lyria 3 Pro rolls out across multiple Google products and platforms:

• Gemini app: Exclusive to paid subscribers
• Google Vids: Video editing application
• ProducerAI: Music production tool acquired by Google last month
• Enterprise tools: Vertex AI (public preview), Gemini API, and AI Studio

Google previously integrated music generation into Gemini following Lyria 3's release. The Pro model extends this capability to enterprise customers via Vertex AI and API access.

Training Data and Attribution

Google states that Lyria 3 Pro was trained using data from partners, permissible YouTube content, and Google-owned data. The company claims the model does not directly mimic specific artists but takes "broad inspiration" when users specify artist names in prompts.

All tracks generated by Lyria 3 and Lyria 3 Pro are marked with SynthID, Google's watermark indicating AI-generated content. This labeling emerges as the music industry implements identification and authentication mechanisms. Earlier this week, Spotify released artist review tools to prevent AI-misattributed music, while Deezer launched detection tools for streaming services to identify AI-generated content.

What this means

Lyria 3 Pro represents Google's competitive response to growing demand for AI music generation—a space where Suno and Udio have gained significant traction. The extension to 3-minute tracks removes a primary limitation preventing professional music production use cases. Enterprise access via Vertex AI and APIs signals Google's strategy to monetize music generation through B2B channels rather than consumer subscriptions alone. The emphasis on SynthID marking and structural composition control suggests Google is prioritizing artist protection and production-quality features over maximum creative automation, positioning Lyria against pure-generation competitors.