Google has launched Lyria 3, a generative music model now available within Gemini, giving users a way to create custom soundtracks from simple prompts or photos.
Lyria 3 works like a digital instrument powered by artificial intelligence (AI). Users describe a mood, scene, or idea, such as a nostalgic 1990s alternative track about a rainy day in Manila, and Gemini produces a 30-second song complete with lyrics and cover art. Users can also upload an image, and the system will generate a track that reflects the photo’s tone and atmosphere.
The tool allows detailed control over the output. Users can select genres ranging from upbeat pop to acoustic, and adjust tempo, vocal style, and overall energy. After the first version is generated, additional prompts can refine the track until it matches the intended sound.
The release shows a shift in how people use AI as a creative partner rather than just a productivity tool. According to Google, in the Philippines, where digital platforms are widely used for music remixes, short-form videos, and visual storytelling, AI tools are increasingly part of everyday content creation.
For students, Lyria 3 can be used to score presentations and school projects. Content creators can develop original background music without hiring composers or navigating complex software. Casual users can turn personal moments, such as travel photos or journal-like thoughts, into short musical pieces.
While human emotion remains central to songwriting, Lyria 3 lowers the barrier to experimentation. By combining text, images, and music generation in one platform,
