ComfyCloudMiniMaxMusic3TextToAudioNode - ComfyUI Built-in Node Documentation - ComfyUI

Runs the MiniMax Music 3 workflow on a Comfy Cloud GPU and returns a generated song. The prompt carries the style, instrumentation and mood; lyrics are sung rather than described, and an empty lyric leaves the track instrumental. This is a beta node and is billed by GPU second.

Inputs

Parameter	Description	Data Type	Required	Range
`prompt`	Description of the song: style, instrumentation and mood. Leading and trailing whitespace is removed before submission.	STRING	Yes	1 to 4096 characters
`lyrics`	Words to sing. Leave empty for an instrumental.	STRING	No	0 to 4096 characters
`seed`	Random seed that controls the generated result (default: 42).	INT	Yes	0 to 9223372036854775807
`max_duration`	Longest the track may run, in seconds (default: 120.0). The model can end the song earlier.	FLOAT	Yes	0.04 to 360.0 (step 0.04)
`audio_quality`	Output bitrate. `"V0"` is variable and the highest quality of the three (default: `"V0"`).	COMBO	Yes	`"V0"` `"128k"` `"320k"`

Outputs

Output Name	Description	Data Type
`AUDIO`	The generated song.	AUDIO

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): defc8d97071f2eaef4b00c6df721f4d10756e4867fefa22c1db7b8c3aafb6b7b