Skip to main content
The LTXV Audio VAE Encode node takes an audio input and compresses it into a smaller, latent representation using a specified Audio VAE model. This process is essential for generating or manipulating audio within a latent space workflow, as it converts raw audio data into a format that other nodes in the pipeline can understand and process.

Inputs

ParameterDescriptionData TypeRequiredRange
audioThe audio to be encoded.AUDIOYes-
audio_vaeThe Audio VAE model to use for encoding.VAEYes-

Outputs

Output NameDescriptionData Type
Audio LatentThe compressed latent representation of the input audio. The output includes the latent samples, the sample rate of the VAE model, and a type identifier.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): 0c17491e6d2910febe7dc5c1ecf988c3f160b1a08de70f8c0c4ab52defe897cd