Google has released an advanced version of its music generation model, Lyria 3 Pro. This model can create tracks lasting up to three minutes with customizable features and creative control.
Lyria 3 Pro has a better understanding of composition structure, allowing users to specify elements such as intros, verses, choruses, and transitions.
“Whether you are an app developer, a business representative, a music professional, or just a creative individual, these integrations will enable you to leverage Lyria's advanced music recognition capabilities to expand your creative horizons,” the announcement states.
Lyria 3 Pro is available in a preview version on Vertex AI. With this neural network, organizations can “scale the production of high-quality content—from quickly creating custom soundtracks for games to integrating into creative tools, music, and video platforms.”
The model is integrated into Google AI Studio and the Gemini API, providing “enhanced understanding of musical context and structural integrity.”
In the video editor Vids, both the basic and Pro versions of Lyria 3 allow users to add personalized musical accompaniment. This feature is available to Google Workspace users and subscribers of Google AI Pro and Ultra.
The Gemini chatbot now features long tracks created using Lyria 3 Pro, with expanded model settings that “offer more room for experimentation.”
Lyria 3 Pro has also been added to ProducerAI, a service for collaborative music creation. Along with the new LLM, it offers an interactive interface for creating complete compositions.
Recall that in March, OpenAI integrated the music recognition service Shazam into ChatGPT.
In the same month, the AI-generated music group Neon Oni planned live concerts in Japan.