bzikst/minimax-music3
MiniMax-Music3: full songs from lyrics and a style description. Serves the official sglang-omni pipeline and returns stereo m4a/AAC by default. Detects available GPUs and colocates or splits the autoregressive and acoustic stages accordingly.
Run bzikst/minimax-music3 with an API
Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.
Input schema
The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| lyrics |
string
|
Song lyrics. Section tags ([verse], [chorus] and others) must each be on their own line.
|
|
| caption |
string
|
|
Complete style description. When set, the three fields below are ignored.
|
| global_metadata |
string
|
|
Tempo, key, genre, emotional arc, overall sonic character.
|
| vocal_details |
string
|
|
Vocal gender and timbre, delivery style, backing vocals, processing.
|
| arrangement |
string
|
|
Instruments per section, rhythmic development, textures and transitions.
|
| duration_seconds |
integer
|
300
Min: 5 Max: 360 |
Upper bound on duration. The model ends the song on its own, almost always before the bound.
|
| seed |
integer
|
Generation seed. Empty means random. The same seed with the same input yields a byte-identical track.
|
|
| response_format |
None
|
m4a
|
Output format.
|
{
"type": "object",
"title": "Input",
"required": [
"lyrics",
"seed"
],
"properties": {
"seed": {
"type": "integer",
"title": "Seed",
"x-order": 6,
"description": "Generation seed. Empty means random. The same seed with the same input yields a byte-identical track."
},
"lyrics": {
"type": "string",
"title": "Lyrics",
"x-order": 0,
"description": "Song lyrics. Section tags ([verse], [chorus] and others) must each be on their own line."
},
"caption": {
"type": "string",
"title": "Caption",
"default": "",
"x-order": 1,
"description": "Complete style description. When set, the three fields below are ignored."
},
"arrangement": {
"type": "string",
"title": "Arrangement",
"default": "",
"x-order": 4,
"description": "Instruments per section, rhythmic development, textures and transitions."
},
"vocal_details": {
"type": "string",
"title": "Vocal Details",
"default": "",
"x-order": 3,
"description": "Vocal gender and timbre, delivery style, backing vocals, processing."
},
"global_metadata": {
"type": "string",
"title": "Global Metadata",
"default": "",
"x-order": 2,
"description": "Tempo, key, genre, emotional arc, overall sonic character."
},
"response_format": {
"enum": [
"m4a",
"mp3",
"opus",
"flac",
"wav"
],
"type": "string",
"title": "response_format",
"description": "Output format.",
"default": "m4a",
"x-order": 7
},
"duration_seconds": {
"type": "integer",
"title": "Duration Seconds",
"default": 300,
"maximum": 360,
"minimum": 5,
"x-order": 5,
"description": "Upper bound on duration. The model ends the song on its own, almost always before the bound."
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
{
"type": "string",
"title": "Output",
"format": "uri"
}