Skip to main content
The EmptyAceStepLatentAudio node creates empty latent audio samples of a specified duration. It generates a batch of silent audio latents filled with zeros, where the length is calculated based on the input seconds and audio processing parameters. This node is useful for initializing audio processing workflows that require latent representations.

Inputs

ParameterDescriptionData TypeRequiredRange
secondsThe duration of the audio in seconds (default: 120.0)FLOATYes1.0 - 1000.0
batch_sizeThe number of latent images in the batch (default: 1)INTYes1 - 4096

Outputs

Output NameDescriptionData Type
outputReturns empty latent audio samples with zeros. The output contains a samples tensor and a type field set to “audio”.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): be20317ed22bf89eeb35a31de0177842f366105da8653e6d7af71241a84967a0