●Detection · Voice

Voice clone and live call detection.

Check recordings and voice messages for cloned voices and synthetic speech. Live call monitoring watches for deepfake callers in real time.

Scan voice →Get the extension
Multi-model detection<3s per imageZero retention
voicemail_0931.wavscan complete
Scan result
AI-generated
0.93LIKELIHOOD
Synthetic voice
Voice print
93
Cadence
84
Spectral artefacts
79
Background noise
52
LiveVoice detection
<3sPer audio clip
0Audio retained
FreeNo account needed

●Platform

Detect it. Explain it. Act on it.

Every scan returns the same three things: a result, the signals that produced it, and a decision you can route on.

voicemail_0931.wavupload · 10:42:08
AI-generated
voicemail_932.wavintake · 10:42:11
Real
voicemail_933.wavintake · 10:42:15
AI-generated

01

Detect

Every file is scanned by independent models for images, video and faces, in the web tool, the extension or by API.

Voice print
93
Cadence
84
Spectral artefacts
79
Background noise
52

3 / 4 signals corroborateCalibrated likelihood

02

Explain

See which signals fired and how strongly. No single model decides; every result comes with its reasons.

Real
Synthetic
Hold the call

Rule: likelihood ≥ 0.85 → Synthetic<3s

03

Route

Branch your workflow on the result. Clean items pass, flags go to review with a full audit trail.

●Coverage

What voice detection covers.

Cloned voices, text-to-speech and live call monitoring.

Audio

Cloned voicesText-to-speechVoice messagesCall recordings

Live

Phone callsVideo callsContact center lines

●Method

What a voice check looks at.

Each check runs as an independent model. Results corroborate before a result is returned.

01

Cloned voices

Speech built from a few seconds of a real voice.

02

Text-to-speech

Synthetic speech from generators.

03

Cadence

Breathing and pauses that are too regular.

04

Spectral artefacts

Patterns left by voice generators.

05

Live calls

Alerts raised while the call is still happening.

06

Face and voice together

Deepfake video calls checked on both signals.

The pipeline

A detector for each kind of media.

Image, video and voice each have their own detector. Their findings come back as one clear answer you can act on.

Image

Diffusion, GAN and face-swap images from Midjourney, DALL·E, Stable Diffusion, Flux and Firefly.

Live

Video

Face swaps across 32 frames and fully generated video from Runway, Kling, Veo and Pika.

Live

Voice

Cloned and synthesised speech in calls, notes and recordings.

Live

What you get

Each file is marked Real, Synthetic or Hold the call, with the likelihood, signals and audit ID behind it.

One answer

●Who it is for

Wherever a voice asks for trust.

Is this voice message really from my relative?

Detect voice cloning and synthetic callers in real time.

Callers authorising transfers.

Wire requests that sound like the CEO.

Phone screens and recorded interviews.

●How it works

Three steps. One result.

01

Upload or paste a URL

WAV, MP3, M4A or MP4 audio. Drag and drop, paste, or enter a link.

02

Voice analysis

Dedicated voice models check for cloning, TTS and spectral artefacts.

03

Clear result

Real or synthetic, with the signals that decided it.

●Integration

Three ways in.
Start with the web app.

Scan in the web app or Chrome extension today. The REST API and MCP server for your AI agents are coming soon. Same detectors, same result, same audit trail.

Web app

Available

Upload in the web app. Images, video and voice, up to 50 MB. Full results in seconds.

witness.vision/scan
Page media● Scan
voicemail_0931.wav · AI-generated · 0.93

Chrome extension

Available

Scan any image or video from inside the tools your team already uses. No download, no upload.

portal.example.com
Page media● Scan
voicemail_0931.wav · AI-generated · 0.93

API

Soon

Single scans, batch jobs and webhooks. Structured JSON with result, likelihood, signals and audit ID.

POST /v1/detect
curl -X POST https://witness.vision/api/v1/detect \
  -H "Authorization: Bearer $WITNESS_KEY" \
  -H "Content-Type: application/json" \
  -d '{"media_url": "https://…/voicemail_0931.wav"}'

→ 200 OK · 412ms
result: ai_generated · 0.93

●Why Witness

Built to be checked.

We say what the system does, what it returns and where its limits are.

Specialized models

Detection built per signal

Specialized models per signal, so you get more coverage and fewer false positives than one classifier.

Explainable

Reasons, not just a score

Every result shows the signals behind it and where in the file they fired.

Zero retention

Analysed, then gone

Media is never stored, shared or used for training.

C2PA

Provenance, when it exists

Reads Content Credentials from capture device to current file.

●Explore

One engine. Every surface.

The same detection, result and audit trail across every team that handles media.

Enterprise

Insurance

Screen damage photos and injury documentation for AI generation before they reach your adjusters.

Explore →

Enterprise

Legal

Know which exhibits warrant forensic review.

Explore →

Enterprise

Fraud detection

Detect AI-generated images, face-swapped video and cloned voices inside your fraud stack.

Explore →

Enterprise

E-commerce

Screen damage, missing-item and not-as-described evidence for AI generation and reuse, before the refund is issued..

Explore →

Product

Chrome extension

Scan media on any site, social feeds, news, claims portals, case files, and get a result in the side panel..

Explore →

●FAQ

Common questions.

Something else? Talk to our team

When will voice detection launch?

Voice detection is live. Upload audio or use the Chrome extension.

Will it work on live calls?

Yes. Live call monitoring is available with the Chrome extension.

Is audio stored?

No. Audio is analysed and discarded.