LTXVEmptyLatentAudio - ComfyUI Built-in Node Documentation

The LTXV Empty Latent Audio node creates a batch of empty (zero-filled) latent audio tensors. It uses the configuration from a provided Audio VAE model to determine the correct dimensions for the latent space, such as the number of channels and frequency bins. This empty latent serves as a starting point for audio generation or manipulation workflows within ComfyUI.

Inputs

Parameter	Description	Data Type	Required	Range
`frames_number`	Number of frames. The default value is 97.	INT	Yes	1 to 1000
`frame_rate`	Number of frames per second. The default value is 25.	INT	Yes	1 to 1000
`batch_size`	The number of latent audio samples in the batch. The default value is 1.	INT	Yes	1 to 4096
`audio_vae`	The Audio VAE model to get configuration from. This parameter is required.	VAE	Yes	N/A

Note: The audio_vae input is mandatory. The node will raise an error if it is not provided.

Outputs

Output Name	Description	Data Type
`Latent`	An empty latent audio tensor with the structure (batch_size, z_channels, num_audio_latents, audio_freq) configured to match the input Audio VAE. The output also includes 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): 1b0ecbeb1388d952f5c5178cdc70bb06aad1640112a0851802c387594629f4bf

LTXVAudioVAEEncode - ComfyUI Built-in Node Documentation

VAEDecodeAudio - ComfyUI Built-in Node Documentation

⌘I

​Inputs

​Outputs

Inputs

Outputs