●Detection · Video

AI video detector.

Find out if a video was generated by AI or contains a face swap. Frame-by-frame analysis that shows which frames triggered the result.

Scan a video →Get the extension
Multi-model detection<3s per imageZero retention
clip_0412.mp4 · 00:18scan complete
Scan result
blend boundary
motion incoherence
frames 96–128
AI-generated
0.90LIKELIHOOD
AI-generated
Temporal consistency
90
Spatial artefacts
85
Face geometry · 32 frames
72
Lip–audio sync
48
<3sPer image
10+Generators covered
0Files 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.

clip_0412.mp4 · 00:18upload · 10:42:08
AI-generated
clip_413.mp4 · 00:18intake · 10:42:11
Real
clip_414.mp4 · 00:18intake · 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.

Temporal consistency
90
Spatial artefacts
85
Face geometry
72
Lip–audio sync
48

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
AI-generated

Result: AI-generated · 0.92<3s

03

Decide

A plain-language result, Real or AI-generated, with a likelihood and the reasons behind it.

●Coverage

Two categories of manipulation.

Separate specialised models for each, not an image classifier run on frames.

Face swaps

Face replacementReenactmentLip-sync manipulationIdentity swap

Generated video

Runway Gen-4.5Kling 3.0Google Veo 3.1Pika 2.5MiniMax H3Luma

●Method

What a scan checks.

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

01

Temporal consistency

Facial geometry, blending boundaries and motion coherence across 32 frames.

02

Spatial artefacts

Patterns left by video generation models in individual frames.

03

Audio–visual sync

Lip movement against audio, for reenactment and dubbing.

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 or AI-generated, with the likelihood, signals and audit ID behind it.

One answer

●When it matters

Wherever video is evidence.

Check a recording for face-swap artefacts the eye can’t catch.

Check before sharing, catch scenes from Runway, Kling and others.

Verify dashcam, CCTV and bodycam footage for investigators.

Verify source video before publishing.

Screen video exhibits frame by frame.

Confirm the person in a recorded interview is who they claim.

●How it works

Three steps. One result.

01

Upload a video

MP4 up to 50 MB. Clips over 30s get a built-in trimmer.

02

Frame-by-frame analysis

Specialised detectors examine sampled frames and the motion between them.

03

Result with frames

Real or AI-generated, plus which frames triggered 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
clip_0412.mp4 · AI-generated · 0.90

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
clip_0412.mp4 · AI-generated · 0.90

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://…/clip_0412.mp4"}'

→ 200 OK · 412ms
result: ai_generated · 0.90

●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

Can AI-generated video be detected?

Yes. Generated video carries temporal and spatial artefacts, in motion, lighting and facial geometry, that trained detectors can measure.

How does face-swap detection work?

Temporal analysis across 32 frames looks for inconsistencies in facial geometry, blending boundaries and motion coherence.

How long can a video be?

Up to 50 MB. For clips longer than 30 seconds, select the segment to analyse.