MiniMax has released MiniMax-Music3, an open-weights model capable of generating complete five-minute songs from text inputs. The model accepts lyrics with section tags and a detailed music description, producing 32 kHz, 16-bit stereo WAV audio. Its architecture combines a Hybrid-LM, consisting of an 8B Global LLM and a 0.6B Local LLM, with a continuous synthesis stack utilizing flow matching and a Flow-VAE. MiniMax has made the weights, inference code, and serving paths publicly available, allowing for commercial use under specific conditions. AI
IMPACT Enables creators and businesses to generate full songs from text, potentially impacting music production, game development, and advertising.
RANK_REASON Open-weights model release from a frontier lab (MiniMax). [lever_c_demoted from frontier_release: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
