Breeze Voice Clone - ComfyUI Built-in Node Documentation

Creates a Breeze voice from a recording of one speaker. The voice is saved to your account and returned as a voice handle, together with an audio preview of how it sounds.

Inputs

Parameter	Description	Data Type	Required	Range
`audio`	Recording of one speaker, at least 3 seconds long. Only the first 60 seconds are used.	AUDIO	Yes	-
`remove_background_noise`	Cleans the recording up before cloning. Default: false.	BOOLEAN	No	true false
`seed`	Controls whether the node re-runs; results are non-deterministic regardless of the seed. Default: 42.	INT	No	0 to 2147483647

Outputs

Output Name	Description	Data Type
`voice`	The new Breeze voice, for Breeze Text to Speech.	BREEZE_VOICE
`preview`	Audio preview of the cloned voice.	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): 3c2e461a8e1a38bfa494a687f5b77a375e9e81c77964493181d7c622a682c56f