POST VC Inference
Last updated
Last updated
POST
/v1/inferences-vc
Creates a voice conversions and adds it to the inference queue. All requests must be made as multipart form requests. The response will contain the job status.
Content-Type
multipart/form-data
x-api-key
<token>
modelId
string
Name of the user
indexRate
number
Influence exerted by the index model
default=0.76 min=0 max=1
rmsMixRate
number
Fusion ratio for replacing the input volume envelope with the output volume envelope
default=1 min=0 max=1
filterRadius
integer
median filter in the result of the pitch recognition of the crop
default=3 min=0 max=7
audioInfer
binary
Support wav, mp3 or flac. Max file size is 50MB.
The parameters "audioInfer" and "modelId" are mandatory for the correct functioning of the application.