Skip to main content
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
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

ParameterData TypeRequiredRangeDescription
audioAUDIOYes-The audio to be encoded.
audio_vaeVAEYes-The Audio VAE model to use for encoding.

Outputs

Output NameData TypeDescription
Audio LatentLATENTThe compressed latent representation of the input audio. The output includes the latent samples, the sample rate of the VAE model, and a type identifier.