MiniMax Launches Music 3: Generates Up to 5-Minute Complete Songs
huggingface · x · 2026-08-14
MiniMax has released MiniMax Music 3, a high-performance music generation model, on Hugging Face. The model generates complete songs up to five minutes long based on lyrics and detailed music descriptions, maintaining long-range coherence, expressive vocals, and evolving arrangements.
Technical Architecture:
- Combines an 8B Global LLM for long-range musical structure and a 0.6B Local LLM for frame-level acoustic details.
- Uses a continuous hidden-state synthesis system based on Flow Matching and Flow-VAE.
- Outputs 32 kHz, 16-bit stereo WAV audio.
Fine-Grained Control: Accepts lyrics (with section tags like [Verse] and [Chorus]) and structured music descriptions (covering genre, BPM, key, vocal gender/timbre, etc.) for precise control.
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