●Detection · Face swaps
Face swap detection.
Find out if the face in a photo or video has been replaced, reenacted or lip-synced. Frame-by-frame analysis that shows where the swap breaks.
●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.
01
Detect
Every file is scanned by independent models for images, video and faces, in the web tool, the extension or by API.
3 / 4 signals corroborateCalibrated likelihood
02
Explain
See which signals fired and how strongly. No single model decides; every result comes with its reasons.
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
Four kinds of face manipulation.
Trained on the open-source and commercial tools used to make them.
Types
Tools
●Method
Where a swap gives itself away.
Each check runs as an independent model. Results corroborate before a result is returned.
01
Blend boundaries
The seam where a generated face meets the real head, hairline and jaw.
02
Facial geometry
Proportions and landmarks that drift from frame to frame.
03
Temporal coherence
Flicker, warping and motion that doesn’t follow the head.
04
Lip–audio sync
Mouth movement that doesn’t match the audio track.
05
Lighting
Shading on the face that disagrees with the scene.
06
Single images
Swap artefacts in stills, profile photos and ID selfies.
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.
LiveVideo
Face swaps across 32 frames and fully generated video from Runway, Kling, Veo and Pika.
LiveVoice
Cloned and synthesised speech in calls, notes and recordings.
LiveWhat 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 a face is proof.
Check a recorded call when someone doesn’t look quite right.
Catch swapped faces in profile photos and video.
Confirm the person in a recorded interview is who they claim.
Screen selfies and liveness recordings for swaps.
Screen video exhibits frame by frame.
Check if a video of you has been faked.
●How it works
Three steps. One result.
Upload a photo or clip
JPG, PNG, WebP or MP4 up to 50 MB.
Face tracking
Faces are located and tracked across up to 32 frames.
Result with frames
Real or AI-generated, with the frames and regions 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
AvailableUpload in the web app. Images, video and voice, up to 50 MB. Full results in seconds.
Chrome extension
AvailableScan any image or video from inside the tools your team already uses. No download, no upload.
API
SoonSingle scans, batch jobs and webhooks. Structured JSON with result, likelihood, signals and audit ID.
curl -X POST https://witness.vision/api/v1/detect \ -H "Authorization: Bearer $WITNESS_KEY" \ -H "Content-Type: application/json" \ -d '{"media_url": "https://…/video_call_recording.mp4"}' → 200 OK · 412ms result: ai_generated · 0.94
●Why Witness
Built to be checked.
We say what the system does, what it returns and where its limits are.
Detection built per signal
Specialized models per signal, so you get more coverage and fewer false positives than one classifier.
Reasons, not just a score
Every result shows the signals behind it and where in the file they fired.
Analysed, then gone
Media is never stored, shared or used for training.
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 →What is a face swap deepfake?
A video or image where one person’s face has been replaced with another’s, or re-animated to say or do something they didn’t.
Can Witness detect face swaps in photos?
Yes. Stills are checked for blend boundaries, geometry and lighting inconsistencies.
How is this different from the AI video detector?
The video detector also catches fully generated video. This page covers the face-specific checks used in both.