We’re launching Lyria 3.5 in Google Flow Music, with advances across musicality, lyrics, vocals, and creative control

Details

Google DeepMind has released Lyria 3.5, its newest music generation model, integrated directly into Google Flow Music. The update addresses four areas simultaneously: musicality (richer, more complex melodic structures that sound more natural), lyrics (higher quality with improved prompt adherence and structural awareness), vocals (more realistic, emotionally nuanced expression with improved pronunciation), and creative control (direct tempo and duration parameters). The announcement is brief and comes from the official DeepMind blog, so specific benchmark comparisons against Lyria 3 or competitor models are not provided. The improvements described—particularly emotionally nuanced vocals and structural lyrics awareness—address areas where AI music generation has faced persistent criticism for sounding repetitive and lacking narrative structure. The integration within Google Flow Music rather than as a standalone API suggests DeepMind's current strategy is to build music generation as a consumer product feature first rather than a developer platform. This positions Lyria differently from music generation tools like Suno and Udio, which offer direct API and creator-facing access. For AI music creators and product builders, the lack of a standalone API announcement means Lyria 3.5 capabilities are currently only accessible through Flow Music. No pricing changes were announced.