Google unveils Lyria 3 Pro for advanced AI music creation of songs up to 3 minutes long

Google has launched Lyria 3 Pro, the most advanced version of its music generation AI model, coming one month after the release of Lyria 3. Lyria 3 Pro allows users to generate full tracks up to three minutes, with the ability to prompt for advanced musical elements such as intros, verses, choruses, and bridges, enhancing creative options for experimentation and facilitating more complex song structures.

Besides supporting longer and more customizable compositions, Lyria 3 Pro is now widely accessible. Businesses can test it in public preview through Vertex AI, while developers and creators can use it in Google AI Studio, the Gemini API, and Google Vids, the company's AI-powered video creation app. Paid subscribers to the Gemini app receive early access to extended music generation, and ProducerAI integration offers iterative capabilities for artists, producers, and songwriters at any level.

In response to concerns about intellectual property and authentic artistry, Google has built in specific safeguards. Lyria 3 Pro avoids reproducing the work of named artists, applying prompts only as broad inspiration, and employs filters to prevent outputs that match existing content. To reinforce transparency, every Lyria 3 and Lyria 3 Pro output embeds Google's SynthID, an imperceptible watermark identifying AI-generated audio.