MiniMax Releases Open-Weights Music Model Music3 for 5-Minute Full Songs
BanghuaZ · x · 2026-08-14
MiniMax has introduced MiniMax-Music3, a new open-weights music generation model. Conditioned on lyrics and detailed music descriptions, it can generate complete songs up to five minutes long with structural coherence, expressive vocals, and stable long-form audio quality.
The architecture combines several components:
- 8B Global LLM: Manages long-range musical structure.
- 0.6B Local LLM: Handles frame-level acoustic details.
- Continuous hidden-state synthesis system: Based on Flow Matching and Flow-VAE.
The model outputs 32 kHz, 16-bit stereo WAV audio. It also supports fine-grained control, allowing users to use structured tags (e.g., verse, chorus, bridge) and metadata (genre, BPM, emotion) for precise customization. The model is now available on Hugging Face and can be served using SGLang.
Related event: MiniMax Open-Sources Music 3 Model for 5-Minute Song Generation(23 posts)→
More from Models
- willcb: Opus 5.5 doesn't smell bigger, it smells like they fixed the data — willcb · 2026-10-16
- Unverified claim: Apple and Meta's 816B-parameter Muse Spark Open runs on two Mac Studios — TansuYegen · 2026-10-16
- Gemini 4 model card: model eliminated months of trial-and-error on bioweapons research — Puzzleheaded-King584 · 2026-10-16
- Every AI picks 7: Anthropic engineer's rule for escaping model taste convergence — rubenhassid · 2026-10-16
- Brain teaser: strip all attention, MLP and embedding matrices from a Llama 3 — how many trainable params remain? — Sauers_ · 2026-10-16
- Lean v4.35.0 ships verified kernels — one written and proven consistent by Claude — geoffreyirving · 2026-10-16