Our Celebrity Voice Detection API detects the presence of well-known figures in audios and videos. Powered by our voice recognition technology, Celebrity Voice Detection identifies over 500 celebrities, politicians, and well-known public figures.
Given an input audio/video, the model detects all celebrity voices present and returns a bounding box (defined as a set of vertices) and a match for each, as well as a confidence score. It also returns an attribute category, which describes what type of famous figure the recognized individual is.
In this API's JSON response, class is defined as a string corresponding to the name of the matching famous figure. If the voice is not matched with any figure in the index, it is not included in the response. If there are no matches found, the bounding_poly property of the response will be empty.
An example of JSON response is shown below:
"status": [
{
"response": {
"input": {
"charge": 0.00004,
"created_on": "2026-08-03T21:13:45.639Z",
"hash": "749235695bb2c7acf02ac9255b985992",
"id": "36654b70-8f80-11f1-b2cb-514c95b6c490",
"inference_client_version": "1",
"media": {
"duration": 11.2,
"filename": "TEST_FILENAME",
"height": 1274,
"mime_type": "mp4",
"mimetype": "video/mp4",
"num_frames": 4,
"type": "VIDEO",
"url": null,
"width": 716
},
"model": "MODEL_NAME",
"model_type": "VOICE_SEARCH",
"model_version": 1,
"project_id": "PROJECT_ID",
"user_id": "USER_ID"
},
"output": [
{
"classes": [
{
"category": "Film",
"class": "Tom Cruise",
"score": 0.9747974973917006
}
],
"time": 0
},
{
"classes": [
{
"category": "Film",
"class": "Tom Cruise",
"score": 0.9699491131305694
}
],
"time": 2.5
},
{
"classes": [
{
"category": "Film",
"class": "Tom Cruise",
"score": 0.9656911617517472
}
],
"time": 5
}
]
},
"status": {
"code": "0",
"message": "SUCCESS"
}
}
]