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
Transforms existing audio samples into new high-quality compositions using text instructions. This node takes an input audio file and modifies it based on your text prompt to create new audio content.

Inputs

ParameterData TypeRequiredRangeDescription
modelCOMBOYes”stable-audio-2.5”
The AI model to use for audio transformation
promptSTRINGYesText instructions describing how to transform the audio (default: empty)
audioAUDIOYesAudio must be between 6 and 190 seconds long
durationINTNo1-190Controls the duration in seconds of the generated audio (default: 190)
seedINTNo0-4294967294The random seed used for generation (default: 0)
stepsINTNo4-8Controls the number of sampling steps (default: 8)
strengthFLOATNo0.01-1.0Parameter controls how much influence the audio parameter has on the generated audio (default: 1.0)
Note: The input audio must be between 6 and 190 seconds in duration.

Outputs

Output NameData TypeDescription
audioAUDIOThe transformed audio generated based on the input audio and text prompt