Skip to main content
POST
Audio classification pipeline

Body

application/json

Request to classify audio inputs.

inputs
required

Audio input as numpy-like array, raw bytes or a dict descriptor. Required.

top_k
integer
default:5

Number of top labels to return.

function_to_apply
enum<string>
default:softmax

Post-processing function to apply to raw model scores.

Available options:
sigmoid,
softmax,
none

Response

200 - application/json

List of label/score dicts

label
string

Predicted label name.

score
number

Confidence score (probability-like) for the label.