Google DeepMind Releases Lyria 3.5, Integrated into Flow Music
Google DeepMind officially released music generation model Lyria 3.5, integrated directly into Google Flow Music. The new version achieves significant breakthroughs in vocal synthesis and music arrangement, generating high-quality full songs from a single text prompt while offering creators greater professional control. This release marks a shift from basic text-to-music to professional production tools.
Confirmed
- The model is integrated into Flow Music with stronger prompt adherence, accurately understanding creative direction.
- Vocals are more expressive and dynamic; arrangements are richer and more natural.
- New BPM control and full-track stem export enhance flexibility for professional music creation.
- A single prompt can generate a complete song; users have already produced high-quality works.
Why it matters
- Lyria 3.5's release marks AI music generation moving from basic text-to-music toward professional production tools. Features like multi-track export and BPM control enable not only rapid high-quality generation but also seamless integration into professional workflows.
2026-07-30 ~ 2026-07-31 · 5 related posts
Primary sources
- [source] Google DeepMind releases Lyria 3.5 and plugs it into Flow Music — GoogleLabs · 2026-07-30
- Google DeepMind Launches Lyria 3.5 Music Model with Enhanced Vocals and Stems Export — jasonbaldridge · 2026-07-30
- [source] Google Drops Lyria 3.5: Music Model Adds BPM Control and Stem Export — chrisfirst · 2026-07-30
- Google Launches Lyria 3.5: Generate High-Quality Songs from a Single Prompt — eyishazyer · 2026-07-31
1 near-duplicate retellings: GoogleLabs