Google has expanded its capabilities in artificial intelligence-powered audio production with the launch of Lyria 3 Pro, the company announced on Thursday, March 26, 2026. The new model represents the most advanced iteration to date, enabling the creation of sound effects and complete musical pieces up to three minutes in length – a significant increase from the 30-second limit of previous versions.
Lyria 3 Pro demonstrates a deeper understanding of musical structure, differentiating between elements like intros, verses, choruses, and bridges. This allows users more precise control over the composition process compared to Lyria 3, which was released in February. The development underscores the rapid advancements in AI technologies within the creative music space.
The model operates similarly to other AI music generation tools such as Suno and Udio, requiring only a description of the desired mood, style, or instruments to generate a complete track. According to aitnews.com, Google is making Lyria 3 Pro available across several of its products and services.
Specifically, the tool is integrated into the Gemini app for paid subscribers, within Google Vids for Workspace users, and on the Vertex AI platform for businesses. It’s also accessible through Google AI Studio and the Gemini API for developers. This integration allows for the direct creation of audio and sound effects within existing workflows, enhancing its utility in media production and content creation.
Almasryalyoum.com reports that Google utilized data from its partners and permissibly sourced data from YouTube to train the model, ensuring it does not mimic any specific artist. The release of Lyria 3 Pro follows the initial launch of Lyria 3 just one month prior, signaling Google’s commitment to rapid innovation in the field of AI-driven music generation, as noted in mobtada.com.
