Detector24
Back to Model Catalogue
Voice Deepfake Detection
AudioSpeech Analysis

Voice Deepfake Detection

Detect AI-generated or cloned voices

Accuracy
87.4%
Avg. Speed
2.4s
Per Request
$0.0150
API Name
voice-deepfake-detection

API Reference

Version
2601
Jan 3, 2026
Avg. Processing
2.4s
Per Request
$0.015
Required Plan
trial

Input Parameters

Detects deepfake audio and synthetic speech from TTS systems

audio_urlstringRequired

URL of audio file to check for deepfake/synthetic speech

Example:
https://example.com/voice.mp3

Response Fields

Deepfake audio detection result

is_bonafideboolean

True if authentic real voice

Example:
true
is_spoofboolean

True if AI-generated/deepfake audio detected

Example:
false
bonafide_probabilityfloat

Probability that audio is real (0.0-1.0)

Example:
0.94
spoof_probabilityfloat

Probability that audio is deepfake (0.0-1.0)

Example:
0.06
confidencefloat

Detection confidence (0.0-1.0)

Example:
0.96
labelstring

Classification result

Example:
bonafide

Complete Example

Request

{
  "model": "voice-deepfake-detection",
  "audio_url": "https://example.com/voice.mp3"
}

Response

{
  "success": true,
  "data": {
    "is_bonafide": true,
    "is_spoof": false,
    "bonafide_probability": 0.94,
    "spoof_probability": 0.06,
    "confidence": 0.96,
    "label": "bonafide"
  }
}

Additional Information

Rate Limiting
If we throttle your request, you will receive a 429 HTTP error code along with an error message. You should then retry with an exponential back-off strategy, meaning that you should retry after 4 seconds, then 8 seconds, then 16 seconds, etc.
Supported Formats
mp3, wav, ogg, flac
Maximum File Size
10MB
Tags:deepfakevoice-cloneaifraud

Ready to get started?

Integrate Voice Deepfake Detection into your application today with our easy-to-use API.

Learn more about audio moderationBrowse all models