Media GenerationModels 🇺🇸 29.07.2026 20:01

DeepMind launches Lyria 3.5 in Google Flow Music with advances in musicality, lyrics, vocals and creative control

Google/DeepMindGoogle/DeepMind
Google DeepMind has released Lyria 3.5, its latest music generation model, in Google Flow Music. The update brings significant improvements in musicality, lyrics quality, vocal expression, and creative control, allowing users to create richer and more natural-sounding tracks.
Google DeepMind has launched Lyria 3.5, the newest version of its music generation model, now available in Google Flow Music. The model delivers major advancements in musicality, enabling more complex melodic structures that sound natural. It also generates higher-quality lyrics with better adherence to prompts and structural awareness. Vocals have been enhanced with more expression, emotion, realistic nuances, and improved pronunciation. Additionally, users gain greater creative control, with easier manipulation of tempo and output duration. The update is available immediately in Flow Music.
Source: Google DeepMind — original
Our earlier posts on this topic ↓
Fresh news