HeyGenVoiceCloneNode - ComfyUI Built-in Node Documentation

Clone a voice from a recording of one speaker with HeyGen’s Voice 1.0 engine. The node uploads the recording, creates an instant voice clone, waits until HeyGen finishes processing it, and returns the voice_id. Connect that to HeyGen Voice 1.0 Text to Speech, or to custom_voice_id in HeyGen Avatar Video and HeyGen Talking Photo. Creating the clone is free; you are billed for the speech you generate with the voice.

Inputs

Parameter	Description	Data Type	Required	Range
`audio`	Recording of one speaker. Use at least 10 seconds of clear speech; only the first 3 minutes are used.	AUDIO	Yes	N/A
`language`	Language spoken in the recording (default: “auto”).	COMBO	Yes	`"auto"` Multiple language presets
`similarity`	How closely the voice follows the recording (default: “max”).	COMBO	Yes	`"medium"` `"high"` `"extra_high"` `"max"`
`remove_background_noise`	Clean up background noise in the recording before cloning (default: True).	BOOLEAN	Yes	True False
`seed`	Change the seed to clone the recording again; each clone is a slightly different voice (default: 42).	INT	Yes	0 to 2147483647

Note: The voice is created as “ComfyUI Voice” in your HeyGen account, and the node prints the voice_id in the UI so you can copy it for reuse. Leave language on “auto” unless the speaker speaks a language that is easily confused with a closely related one. The seed input includes a fixed Control After Generate control in the UI, so change it by hand when you want another clone.

Outputs

Output Name	Description	Data Type
`voice_id`	The ID of the cloned voice, for reuse in the HeyGen Voice 1.0 Text to Speech node or as a `custom_voice_id`.	STRING

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): 0bf5c7170d140936841cc4afd28022574df8e4c2280137607dcfca8e36862317

​Inputs

​Outputs

Inputs

Outputs