Audio Deepfake / Voice Spoof Detection
Detects synthetic voices, cloned speakers, and audio generated using TTS (Text-to-Speech) models.
The Audio Deepfake Detection API analyzes audio signals to detect synthetic voices, cloned speakers, and speech generated using TTS models.
It identifies spoofing patterns, AI artifacts, and manipulation in recorded audio.
Endpoint
POST /v1/audio/detectRequest Body
| Field | Type | Required | Description |
|---|---|---|---|
file | binary | Yes | Audio file to analyze. |
explain | boolean | No | Returns detailed explanation of detected spoofing. |
transcribe | boolean | No | Enables speech-to-text transcription. |
url | string | No | URL to an audio file (alternative to uploading). |
Example Request (cURL)
curl -X POST "https://forensiz.ai/" \
-H "x-api-key: YOUR_API_KEY" \
-F file=@"/path/audio.mp3"Response Status Codes
| Status Code | Meaning |
|---|---|
| 200 OK | Audio processed successfully. |
| 400 Bad Request | Request is invalid or missing fields. |
| 401 Unauthorized | Missing or invalid API key. |
| 403 Forbidden | Access denied for this API key. |
| 404 Not Found | Endpoint does not exist. |
| 413 Request Entity Too Large | Audio file exceeds the size limit. |
| 415 Unsupported Media Type | Incorrect or unsupported audio format. |
| 500 Internal Server Error | Unexpected error occurred. |