SpeakerScope.ai

Gender Recognition

Predict the gender of the speaker in an audio sample


Request

Endpoint

POSThttps://speakerscope.ai/api/gender

Fields

FieldTypeDescription
audio_urlstringURL of the audio file

Example

import requests

response = requests.post(
    "https://speakerscope.ai/api/gender",
    auth=("<API_KEY>", "<API_SECRET>"),
    json={
        "audio_url": "<AUDIO_URL>",
    },
)

print(response.json())

Response

Fields

FieldTypeDescription
predictionstrPredicted gender ("male" or "female")
probabilitiesdict[str, float]Maps gender labels to their confidence scores, sorted in descending order

Example

{
  "prediction": "male",
  "probabilities": {
    "male": 0.97,
    "female": 0.03
  }
}