Audio model · MiniMax
MiniMax Music 3
Generate complete songs with vocals from a description
What is MiniMax Music 3?
MiniMax Music 3 writes full songs of up to five minutes from a description of the style, mood, vocals and arrangement. Add lyrics with structure tags like [verse] and [chorus] to get a sung performance, or leave them out for an instrumental track.
Capabilities
- Generate songs up to five minutes long from a text description
- Sing your own lyrics, arranged by verse, chorus and bridge
- Generate instrumental tracks when you provide no lyrics
MiniMax Music 3 on Melius
Melius runs MiniMax Music 3 alongside every other major image, video, audio, and text model, so you can generate with it, compare it against the field, and let the Mel agent route to it automatically — all on one infinite canvas. You only pay for what you generate.
Frequently asked questions
What is MiniMax Music 3?
MiniMax Music 3 writes full songs of up to five minutes from a description of the style, mood, vocals and arrangement. Add lyrics with structure tags like [verse] and [chorus] to get a sung performance, or leave them out for an instrumental track.
How do I use MiniMax Music 3 on Melius?
Melius is a node-based canvas: add a node, pick MiniMax Music 3 from the model picker, and connect it to whatever should feed it or follow it. You can also just describe what you want and let the Mel agent wire it up. You only pay for what you generate.