LTXVAudioVAEEncode - ComfyUI Built-in Node Documentation

The LTXV Audio VAE Encode node takes an audio input and compresses it into a smaller, latent representation using a specified Audio VAE model.

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

Parameter	Description	Data Type	Required	Range
audio	The audio to be encoded.	AUDIO	Yes	-
audio_vae	The Audio VAE model to use for encoding.	VAE	Yes	-

Outputs

Output Name	Description	Data Type
Audio Latent	The 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): 68f70e0f8048cd9ba723f52eefc93cc33564eb3e68c0cb9b677964dc99aecb97