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 Text-to-Music Model(14 posts)→
More from Models
- Vercel Offers GLM 5.2 Model Free for eve Agents Until August 27 — cramforce · 2026-08-14
- Deepgram Crosses $100M ARR and Launches Flux TTS Voice Model — deepgramscott · 2026-08-14
- SemiAnalysis: DeepMind Overhaul Signals Gemini's Downfall, GCP Emerges as Winner — ben_j_todd · 2026-08-14
- Musk Offers More Free Usage and Resets Limits for Grok 4.6 Launch — EricBuess · 2026-08-14
- Grok 4.6 Tops GPQA Diamond Leaderboard with 94.9% Score — elonmusk · 2026-08-14
- a16z's Martin Casado Tests Grok 4.6: Impressed by Complex Coding and Long Tasks — elonmusk · 2026-08-14