EmptyLatentAudio - ComfyUI Built-in Node Documentation

Empty Latent Audio creates an empty latent tensor for audio processing. It generates a blank audio latent representation with a specified duration and batch size, which can be used as a starting point for audio generation or processing workflows. The node automatically calculates the appropriate latent dimensions based on the audio duration and sample rate.

Inputs

Parameter	Description	Data Type	Required	Range
`seconds`	The duration of the audio in seconds (default: 47.6)	FLOAT	Yes	1.0 - 1000.0
`batch_size`	The number of latent images in the batch (default: 1)	INT	Yes	1 - 4096

Outputs

Output Name	Description	Data Type
`LATENT`	Returns an empty latent tensor for audio processing with the specified duration and batch size. The tensor has a shape of [batch_size, 64, length], where length is calculated from the audio duration and sample rate. The output also includes metadata indicating the type is “audio” and a temporal downscale ratio of 2048.	LATENT

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): 6ca63d26febe2d87ff751a57044eb81b553b19756f4b3f9478ecb5a733ec0041

​Inputs

​Outputs

Inputs

Outputs