Google Releases Lyria 3.5 AI Music Model for Richer and More Emotional Sound

Google announced the release of Lyria 3.5, its newest AI model dedicated to music creation, following the launch of several productivity-focused models (Gemini 3.6 Flash, Gemini 3.5 Flash-Lite, and Gemini 3.5 Flash Cyber) earlier this week. Compared to its predecessor, Lyria 3.5 can generate more layered and intricate music while responding better to prompts and understanding musical structure more deeply, resulting in higher-quality compositions. Google states that vocals produced by the model are more realistic and emotionally expressive. The new model also simplifies music management, giving users more creative control over tempo and duration. Lyria 3.5 is available today on the Google Flow Music web platform, where Google has also posted a sample song generated with the model.