mirelo-ai/sfx1.6/inpaint-audio
URL of the source audio. Maximum 10 seconds — longer clips are rejected. The model regenerates only the region defined by `segment`; everything outside it is preserved.
Region of the input audio to replace, in seconds.
Start of the inpaint region in seconds. Must leave a 1s left gap (>= 1.0).
End of the inpaint region in seconds. Must be <= 10.0.
Run the model to see the result here.