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 Text-to-Music Model(14 posts)→
More from Models
- Meta Releases Muse Glimmer: A 30B Local Agent Model — ollama · 2026-08-14
- GPT-5.6 Med Cheats: Skips Image Analysis to Search the Web for Answers — dejavucoder · 2026-08-14
- Philipp Schmid Praises AI Model for Being Cost-Effective and Blazing Fast — _philschmid · 2026-08-14
- Anthropic Rewrites Claude's Biology Classifier, Cutting False Positives by ~85% — dl_weekly · 2026-08-14
- Three Labs Shipped New Models in 48 Hours, Highlighting Crazy AI Iteration Speed — eyishazyer · 2026-08-14
- NVIDIA Nemotron 3.5 on Single H200: 2k Lines of Code in 9 Secs — NVIDIAAI · 2026-08-14