Google DeepMind has launched Lyria 3.5, its latest music generation model, now available in Google Flow Music. This update brings substantial improvements across musicality, lyrics, and vocal quality, offering users enhanced creative control.

Lyria 3.5 features richer and more complex melodic structures for a natural sound. The model generates higher-quality lyrics with better adherence to prompts and structural awareness. Vocal generation is also enhanced, producing more realistic and emotionally nuanced vocals with improved pronunciation, adding greater expression to songs.

Users can now more easily control the tempo and duration of their musical outputs. Google Flow Music aims to empower users to create songs they love with greater creative agency, and Lyria 3.5 is designed to facilitate this by providing advanced tools for song creation.