LTXVReferenceAudio - ComfyUI Built-in Node Documentation - ComfyUI

LTXV Reference Audio transfers the voice identity of a speaker from a reference audio clip to generated audio. It encodes the reference audio into the conditioning and optionally patches the model with identity guidance, which runs an extra forward pass without the reference each step to amplify the speaker identity effect.

Inputs

Parameter	Description	Data Type	Required	Range
`model`	The model to be patched with identity guidance.	MODEL	Yes	-
`positive`	The positive conditioning input.	CONDITIONING	Yes	-
`negative`	The negative conditioning input.	CONDITIONING	Yes	-
`reference_audio`	Reference audio clip whose speaker identity to transfer. ~5 seconds recommended (training duration). Shorter or longer clips may degrade voice identity transfer.	AUDIO	Yes	-
`audio_vae`	LTXV Audio VAE for encoding.	VAE	Yes	-
`identity_guidance_scale`	Strength of identity guidance. Runs an extra forward pass without reference each step to amplify speaker identity. Set to 0 to disable (no extra pass). (default: 3.0)	FLOAT	Yes	0.0 - 100.0
`start_percent`	Start of the sigma range where identity guidance is active. (default: 0.0)	FLOAT	Yes	0.0 - 1.0
`end_percent`	End of the sigma range where identity guidance is active. (default: 1.0)	FLOAT	Yes	0.0 - 1.0

Note: Identity guidance is only applied when identity_guidance_scale is greater than 0 and the current sampling step is within the range defined by start_percent and end_percent. The reference audio is resampled to the audio VAE’s sample rate if the two differ.

Outputs

Output Name	Description	Data Type
`model`	The model patched with the identity guidance function.	MODEL
`positive`	The positive conditioning, now containing the encoded reference audio data.	CONDITIONING
`negative`	The negative conditioning, now containing the encoded reference audio data.	CONDITIONING

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): ae15c5838656324667d099614b325b863341f05afda43054658999574522dd49