Detect AI-generated speech
Checks whether a recording contains AI-generated speech. Send one audio file longer than 4 seconds and at most 120 seconds. Use the result's verdict: real, fake, or not_sure when the recording cannot be judged reliably (try a longer or cleaner recording). score (0 to 1, higher means more likely AI-generated) is kept for older clients together with label and is_synthetic. A not_sure verdict uses credits like any result, except when the check could not run completely: then credits.charged is 0. Main failures: the file is not audio or is damaged (415/422), 4 seconds or shorter or longer than 120 seconds (422), not enough credits (402), the service is busy (503, retry later). Requires scope deepfake:detect.
Request
- Base URL: https://platform.detectif.ai
- URL: https://platform.detectif.ai/v1/deepfake/detect
- Auth: HTTP bearer
Headers
Optional (recommended) key that makes retries safe for 24 h: a retry with the same key and the same request returns the stored response without charging again.
Response
The check completed.
Example response
{
"credits": {
"balance": 4950,
"charged": 50
},
"idempotent_replay": false,
"latency_ms": 412.7,
"model": {
"name": "aletheia",
"version": "3f9c2a71b0d4"
},
"object": "deepfake.detection",
"operation_id": "op_6f1ed002ab5595859014ebf0951522d9",
"request_id": "req_8f14e45fceea167a5a36dedd",
"result": {
"duration_seconds": 6.4,
"is_synthetic": false,
"label": "genuine",
"score": 0.0731,
"score_semantics": "Higher means more likely AI-generated. Decide with the verdict, not the score alone.",
"segments": [
{
"end": 4,
"score": 0.061,
"start": 0
},
{
"end": 6,
"score": 0.085,
"start": 2
}
],
"threshold": 0.62,
"verdict": "real"
}
}Changes
No recorded changes to this operation across all 1 revision of this API.