AI Voice Detector · 50+ engines · 95% accuracy

Cloned voices, caught.

Drop in an audio file or call recording. Detect synthetic speech from ElevenLabs, Resemble, PlayHT, OpenAI, and 50+ other voice-cloning engines.

  • Detects voice clones from all major TTS platforms
  • Integrated AI Noise Remover for noisy phone recordings
  • Multilingual — works across accents and dialects
caller-recording.mp3 · 0:48
AI Voice · ElevenLabs v2
0:000:120:240:360:48
Confidence0.94
Engine matchElevenLabs v2
Pitch contourFlat
Breath gapsAbsent
Spectral edgeQuantized
Noise profileStudio-clean
What it catches

The signals a human ear can't reliably hear.

Synthetic speech is statistically different from human speech. Our model triangulates across six independent signals — the file has to fail multiple before we flag it.

SIGNAL 01

Pitch contour flatness

Real speakers vary pitch involuntarily — micro-fluctuations every 80–150ms. TTS systems smooth them out. We measure the variance.

SIGNAL 02

Missing breath gaps

Humans breathe. Cloned voices often skip the inter-clause inhale or insert a synthetic one of suspiciously consistent duration.

SIGNAL 03

Spectral edge artifacts

Vocoder upsampling leaves a high-frequency quantization signature most TTS engines can't fully suppress — visible at 8kHz+.

SIGNAL 04

Phoneme transition smoothness

Diffusion-based voice clones produce unnaturally smooth phoneme transitions. We compare against a corpus of 200k human speech samples.

SIGNAL 05

Studio-clean noise floor

Phone calls have background noise. A "phone call" with a studio-clean noise floor is one of the strongest deepfake tells.

SIGNAL 06

Engine fingerprint match

Most TTS systems have a unique frequency-response signature. We match against signatures from the 50+ engines we track.

Engines we detect

Every major voice-clone platform.

If a TTS or voice-clone product has been used in a documented attack, our detector knows its fingerprint. Models retrained monthly as new engines ship.

ElevenLabs
Resemble AI
PlayHT
OpenAI Voice
Microsoft Azure
Google WaveNet
Amazon Polly
Murf
Speechify
Descript Overdub
Coqui
Tortoise
XTTS-v2
Bark
+ 36 more
Real cases

The attacks we'd have caught.

Documented voice-clone fraud in the last 24 months. Every one had a clear acoustic signal we'd have flagged inside a second.

Hyderabad · $1,688 lost

A woman in Hyderabad lost Rs 1.4 lakh to a scammer using AI to mimic her nephew's voice. The clone had a flat pitch contour and missing breath gaps — both Signal 01 and 02 flags.

Hong Kong · $25.6M lost

A finance worker was tricked into sending $25M after a deepfake video call with cloned voices of the CFO and colleagues. Studio-clean noise floor on a "Zoom call" — Signal 05 alone would have triggered.

"Mom these bad men have me"

A mother received a fake-kidnapping ransom call using a cloned daughter's voice. The cry-and-plead pattern was tonally consistent across 90 seconds — humans aren't.

Detect Deepfakes Before They Spread.

Free plan ships with 50 detections/month. Starter at $49/mo handles 1,000. Enterprise scales to 20,000.