Google DeepMind has launched Lyria 3.5, the latest version of its music generation model, now available in Google Flow Music. The update brings significant advancements across musicality, lyrics, vocal quality, and creative control, enabling users to craft richer and more expressive tracks.
The new model produces more natural and complex melodic structures, enhancing overall musicality. Lyric generation has been improved with better prompt adherence and structural awareness, resulting in higher quality outputs. Vocals are now more realistic and emotionally nuanced, with improved pronunciation that adds expression and emotion to songs.
Creative control has also been expanded, allowing users to more easily adjust tempo and duration of their creations. Google DeepMind aims to help users create songs they love with greater flexibility and precision.