MiniMax-Music3
Open-weights model that generates complete five-minute stereo songs from lyrics and a style caption.
About
Full songs, not loops, are the target of MiniMax-Music3: given lyrics tagged with markers like [Verse] and [Chorus] plus a caption describing genre, instrumentation, and vocal style, it renders up to five minutes of 32 kHz, 16-bit stereo audio with coherent arrangements. The architecture is hierarchical: an 8B global language model plans semantic tokens and long-range song structure, a 0.6B local model fills in frame-level acoustic detail, and a 2.4B flow-matching stage with a Flow-VAE decoder synthesizes the waveform. MiniMax published the weights on Hugging Face in August 2026 under the MiniMax-Music3 Community License, which permits commercial use with attribution until yearly revenue passes 20 million dollars. Inference runs as a modular diffusers pipeline on a CUDA GPU, needing about 24 GB of VRAM at full precision, around 22 GB with CPU offloading, and 8 GB cards via a slower streaming mode; SGLang-Omni serves it at scale, and ComfyUI added official support at launch. It arrived as the strongest open-weights alternative to hosted services like Suno.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Music & Audio Generation
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- License
- MiniMax-Music3 Community License
- Minimum VRAM
- 8 GB
- Added
- Aug 24, 2026
Related Tools
Latent diffusion model for text-to-audio, music, and speech generation.
Audio super-resolution model for upsampling audio to higher sample rates.
State-of-the-art music source separation model by Meta for splitting tracks.
Fast music generation model producing full songs with lyrics in seconds.
Audio diffusion model by Harmonai for generating music samples.
PyTorch library for deep learning research on audio generation including MusicGen and AudioGen.