Skip to main content
The VAEDecodeAudio node converts latent representations back into audio waveforms using a Variational Autoencoder. It takes encoded audio samples and processes them through the VAE to reconstruct the original audio, applying normalization to ensure consistent output levels. The resulting audio is returned with a standard sample rate of 44100 Hz, or the sample rate from the input samples if provided.

Inputs

ParameterDescriptionData TypeRequiredRange
samplesThe encoded audio samples in latent space that will be decoded back to audio waveformLATENTYes-
vaeThe Variational Autoencoder model used to decode the latent samples into audioVAEYes-

Outputs

Output NameDescriptionData Type
AUDIOThe decoded audio waveform with normalized volume and sample rate (default: 44100 Hz, or the sample rate from the input samples if present)AUDIO
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): 4736b987361bf16ad9c5db1a9f8593646fd7ffb37267aed4396285a2a0e6c1cc