Google launches Lyria 3.5 music model with human-like vocals, now in AI Studio
AI_Andrew · x · 2026-09-06
Google's GenMedia team released Lyria 3.5, a music generation model now available in Google AI Studio with developer documentation.
The standout improvements are in sound design and vocal performance:
- Vocals carry genuine emotional weight, dynamic breath, and phrasing rather than flat synthetic delivery.
- Production: atmospheric deep low-end and beats, with real texture, depth, and spatial warmth instead of compressed or muddy sound.
Developers can try Lyria 3.5 in AI Studio.
Related event: Google's Lyria 3.5 Music Model Rolls Out to All Gemini Users(9 posts)→
More from Multimodal
- FastVideo open-sources MiniMax FastH3 Omni with training code, 12x faster on Blackwell — multimodalart · 2026-10-21
- Megalith 008: stunning AI-generated colossal architecture series — azed_ai · 2026-10-21
- Higgsfield offers $25K prizes for open-source ComfyUI rebuilds of its apps — MuziqueComfyUI · 2026-10-21
- Stunning AI-generated elderly portrait blurs the line with real photography — LudovicCreator · 2026-10-21
- Writer with no drawing skills uses AI to publish third episode of original manga — OriginalMangaStudio · 2026-10-21
- HeyGen's Professional Voice Clone needs just 30 min of audio to sound exactly like you — rohanpaul_ai · 2026-10-21