- Home
- AI Music Generators
- MiniMax Music 3.0
On the recordRead 12 Oct 202626 facts
MiniMax Music 3.0
MiniMax Music 3.0 · founded 2022
On the record
- Audio export formats
- wavminimax.io · read 22 Sep 2026
- Audio output
- The model produces 32 kHz, 16-bit stereo WAV audio.huggingface.co · read 12 Oct 2026
- Availability
- MiniMax says its music models stopped being available through Token Plan and M Plan on August 20, 2026, and directs users to MiniMax Audio or the open-source model weights.platform.minimax.io · read 12 Oct 2026
- Commercial use
- Yesminimax.io · read 22 Sep 2026
- Company
- MiniMax describes itself as a global AI foundation model company founded in early 2022.minimax.io · read 12 Oct 2026
- Company products
- MiniMax says its models power products including MiniMax Code, MiniMax Design, MiniMax Audio, Talkie, and its enterprise and developer-facing Open API Platform.minimax.io · read 12 Oct 2026
- Control caveat
- Section tags and music descriptions guide generation but do not guarantee that tempo, key, instruments, lyrics, or structure will exactly match the request.huggingface.co · read 12 Oct 2026
- Generation limits
- The model card lists a 5,000-token text prompt limit, a 9,000-acoustic-frame audio limit, and non-streaming generation only.huggingface.co · read 12 Oct 2026
- Hardware requirement
- Inference requires CUDA; the model card says automatic CPU offloading can reduce GPU memory needs to about 22 GB, with slower layer-by-layer offloading fitting 8 GB cards.huggingface.co · read 12 Oct 2026
- License
- The MiniMax-Music3 Community License requires commercial products using the software to prominently display “MiniMax-Music3” and requires prior written authorization when aggregate yearly revenue exceeds US$20 million.huggingface.co · read 12 Oct 2026
- Local use
- The official model repository documents downloading the model and running it with Diffusers, including a device-map example using CUDA.huggingface.co · read 12 Oct 2026
- Model access
- MiniMax publishes downloadable model weights and instructions for local use with SGLang, Diffusers, and ComfyUI.huggingface.co · read 12 Oct 2026
- Model components
- The model uses an 8B Global LLM for long-range structure, a 0.6B Local LLM for acoustic detail, and a synthesis stack with flow matching and Flow-VAE.minimax.io · read 12 Oct 2026
- Music controls
- Its inputs can specify lyrics and musical details such as genre, tempo, key, emotion, vocal delivery, instrumentation, arrangement, and production profile.huggingface.co · read 12 Oct 2026
- Open weights
- MiniMax describes Music 3.0 as an open-weights model, and its official Hugging Face repository provides model files for download.huggingface.co · read 12 Oct 2026
- Prompt enhancement
- A template-based Prompt Enhancement System can expand a simple description into detailed musical instructions.minimax.io · read 12 Oct 2026
- Purpose
- MiniMax Music 3 generates complete songs from a creative concept and optional lyrics in a single generation.minimax.io · read 12 Oct 2026
- Song length
- The model is designed to sustain creative intent across songs of up to five minutes.minimax.io · read 12 Oct 2026
