Skip to main content
Transforms part of an existing audio sample using text instructions. This node allows you to modify specific sections of audio by providing descriptive prompts, effectively “inpainting” or regenerating selected portions while preserving the rest of the audio.

Inputs

ParameterDescriptionData TypeRequiredRange
modelThe AI model to use for audio inpainting.STRINGYes"stable-audio-2.5"
promptText description guiding how the audio should be transformed (default: empty). Maximum length is 10,000 characters.STRINGYes
audioInput audio file to transform. Audio must be between 6 and 190 seconds long.AUDIOYes
durationControls the duration in seconds of the generated audio (default: 190).INTNo1 to 190
seedThe random seed used for generation (default: 0).INTNo0 to 4294967294
stepsControls the number of sampling steps (default: 8).INTNo4 to 8
mask_startStarting position in seconds for the audio section to transform (default: 30).INTNo0 to 190
mask_endEnding position in seconds for the audio section to transform (default: 190).INTNo0 to 190
Note: The mask_end value must be greater than the mask_start value. The input audio must be between 6 and 190 seconds in duration.

Outputs

Output NameDescriptionData Type
audioThe transformed audio output with the specified section modified according to the prompt.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): c00d84db73dfcd708495d7a04e21a2378880ca6ceb906473a45dcc1dae20bf79