Google has released Lyria 3.5, the latest version of its AI music generation model, introducing improved control over how music is created. Available through Google Labs’ Flow platform, the update is designed to produce more coherent melodies, stronger vocals and lyrics, and outputs that more closely follow a user’s creative instructions.
Rather than focusing solely on generating complete songs, Google is positioning Lyria 3.5 as a creative tool that helps musicians, marketers and content creators develop ideas more efficiently. The enhanced controls allow users to refine the tempo and duration of their outputs, making the platform more practical for iterative creative workflows.
Key facts
- Google has launched Lyria 3.5 through its experimental Flow music creation platform.
- The model delivers improved melody, lyric and vocal generation.
- Users have greater control over tempo, song structure and creative direction.
- Prompt adherence has been improved, producing outputs that better match user instructions.
- The update is aimed at musicians, video creators and other creative professionals exploring AI-assisted music production.
Our take
The significance of this release is less about AI replacing musicians and more about giving creators better control over the creative process. As generative tools mature, the emphasis is shifting from producing impressive demonstrations to helping users iteratively refine ideas.
For organisations producing marketing, training or multimedia content, tools like Lyria 3.5 may reduce the time needed to develop background music and creative concepts. However, copyright, licensing and brand considerations should still be reviewed before AI-generated music is used commercially.
KiwiGen.AI 