Detect AI-generated or manipulated voice recordings.
This endpoint identifies synthetic voices used in impersonation, fraud calls, or voice authentication bypass attempts.
The API runs asynchronously and returns a job_id. Use the job status endpoint to fetch results.
Use cases: fraud call detection, voice biometric protection, compliance in financial services.
Supported formats: .mp3, .wav, .m4a
Upload an audio file for authenticity analysis
Input audio file
"@audio.mp3"
Audio analysis job created, returns job_id for result tracking
Response payload containing the deepfake analysis results for an image, video, or streaming session.
Job Id
"01827ed4-c928-7a3c-9a30-7ab7cc169d11"
Job Status
queued, completed, failed "completed"
Job Type
image, video, audio "image"
Content Type from original request
"image/jpeg"
File size in bytes
1024
Score of image. Defined only when job has completed successfully
0.985
Verdict of image. Defined only when job has completed
deepfake_likely, deepfake_unlikely "deepfake_unlikely"
Error code of image. Defined only when job has failed
NoFaceDetected, RuntimeError, FaceTooBlurry, FaceTooDark, FaceTooBright, Unknown "NoFaceDetected"
Additional message
"No face detected"
Flag indicates that verification is created in sandbox env
false