Google DeepMind Launches Lyria 3.5 Music Model with Enhanced Vocals and Stems Export
jasonbaldridge · x · 2026-07-30
Google DeepMind has released its latest music generation model, Lyria 3.5, now powering the Flow Music platform.
Key updates in this version include:
- Vocals: More expressive and dynamic singing capabilities.
- Musicality: Richer arrangements with natural-flowing tracks.
- Controls: Better instruction following, featuring new BPM control and exportable stems for full-length songs.
Related event: Google DeepMind Releases Lyria 3.5 Integrated with Flow Music(3 posts)→
More from Multimodal
- HeyGen Launches Video Podcast: Turn Docs into Two-Host Video Shows — eyishazyer · 2026-07-30
- HeyGen's Video Podcast Feels Like a Recorded Show, User Says — hey_abusiddik · 2026-07-30
- Testing AI Video Tool Agent Two: Generating Cinematic Sci-Fi Shorts — LudovicCreator · 2026-07-30
- First Hands-on with MiniMax H3: Supports 12 References for Video Generation — TomLikesRobots · 2026-07-30
- HeyGen Launches Video Podcast: Turn Docs and Links into Multi-Cam Shows — HeyGen · 2026-07-30
- Help Needed: Breaking Through Template Workflows for Chroma and LTX Video Generation — Caramelacurls · 2026-07-30