MiniMax Releases Music 3: Generating Up to 5-Minute Complete Songs
PurzBeats · x · 2026-08-14
MiniMax has released the high-performance music generation model MiniMax Music 3 on Hugging Face, capable of generating complete songs up to 5 minutes long based on lyrics and detailed music descriptions.
Technical Architecture:
- Combines an 8B Global LLM (for long-range musical structure) and a 0.6B Local LLM (for frame-level acoustic detail).
- Uses a continuous hidden-state synthesis system based on Flow Matching and Flow-VAE.
- Outputs 32 kHz, 16-bit stereo WAV audio.
Control Capabilities:
- Accepts dual inputs: lyrics and music descriptions for fine-grained control.
- Lyrics support explicit section tags like [Verse] and [Chorus].
- Music descriptions support structured prompts to precisely define global metadata and vocal details like genre, BPM, key, emotional progression, vocal gender, and timbre.
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