google drops lyria 3.5 in flow, its newest music generation model

Nick Trenkler 30 Jul 2026 1 min read

Illustrated woman in purple jacket summons glowing notes from a neon mixer, evoking Google Lyria 3.5 AI music generation.

what's new:

• musicality – richer, more complex melodic structures that sound more natural
• lyrics – higher quality with better prompt adherence and structural awareness
• vocals – more expression and emotion, more realistic delivery, improved pronunciation
• control – set tempo and duration of outputs more directly

the demo under this tweet was made with lyria 3.5 – the background track is fully model-generated

0:00

/2:36

Meet Lyria 3.5, the newest music model from @GoogleDeepMind, now powering Flow Music:

🎤 Vocals: More expressive, dynamic singing
🎸 Musicality: Richer arrangements with tracks that flow naturally.
🎛️ Controls: Better at following creative directions - now featuring BPM control… pic.twitter.com/DKVtQes0RV
— Google Flow Music (@googleflowmusic) July 29, 2026

glm 5.3 vs kimi k3 – four hogwarts locations in three.js

the setup: streamed straight off @openrouter, no agent loop, no tools, no filesystem – one prompt in, one html file out. the system prompt is a three.js skill, 32,014

21 Aug 2026 1 min read

Illustrated man in jacket with Chinese flag patches holds cash stack, hands $6 receipt to server rack in neon-lit data center

the performance gap between us and chinese models is at a record-low 6% per bloomberg

@rachelmetz, ai reporter at @technology, broke down the cost math: the industry is quietly moving from cost per token to cost per task. not how cheap the model is per

21 Aug 2026 1 min read