Skip to main content
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

ParameterDescriptionData TypeRequiredRange
modelThe AI model to use for audio transformationCOMBOYes”stable-audio-2.5”
promptText instructions describing how to transform the audio (default: empty, max length: 10000 characters)STRINGYes
audioAudio must be between 6 and 190 seconds longAUDIOYes
durationControls the duration in seconds of the generated audio (default: 190)INTNo1-190
seedThe random seed used for generation (default: 0)INTNo0-4294967294
stepsControls the number of sampling steps (default: 8)INTNo4-8
strengthParameter controls how much influence the audio parameter has on the generated audio (default: 1.0)FLOATNo0.01-1.0
Note: The input audio must be between 6 and 190 seconds in duration. The prompt text has a maximum length of 10,000 characters.

Outputs

Output NameDescriptionData Type
audioThe transformed audio generated based on the input audio and text promptAUDIO
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): 4d320c851a58b58d1a744ca64295fe0cf3002455944ea1c5484b0c2df3ecd4d5