●Watermarks · SynthID

SynthID detector.

A free online SynthID checker and AI watermark checker. Upload any image to see if it carries Google’s SynthID signal. For content without watermarks, Witness runs AI detection to catch what watermarks miss.

Check an image →Get the extension
Multi-model detection<3s per imageZero retention
uploaded_image.pngscan complete
Scan result
synthid signal
diffusion texture
no content credentials
SynthID found
0.94LIKELIHOOD
AI-generated
SynthID watermark
100
Generative fingerprint
94
Frequency artefacts
86
C2PA / EXIF
0
SynthIDGoogle watermark
C2PAContent Credentials
EXIFMetadata check
+AIDetection fallback

●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.

uploaded_image.pngupload · 10:42:08
AI-generated
uploaded_image.pngintake · 10:42:11
Real
uploaded_image.pngintake · 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.

SynthID watermark
100
Generative fingerprint
94
Frequency artefacts
86
C2PA / EXIF
0

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

Three layers of verification.

Watermarks are one signal. Witness reads all three.

Watermarks

Google SynthIDOpenAI C2PAElevenLabs audio marksKakao SynthID

Without watermarks

Ensemble AI detectionFrequency analysisFace-swap detectionGenerator attribution

●Method

What a SynthID check covers.

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

01

SynthID watermark

Reads the invisible signal embedded by Google’s AI products: Gemini, Imagen, Veo.

02

C2PA provenance

Signed Content Credentials from OpenAI, Adobe Firefly, and other adopters.

03

AI detection fallback

Most content has no watermark. Witness runs ensemble detection to catch what watermarks miss.

The pipeline

A detector for each kind of media.

Image and video 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

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

For anyone who sees content and wonders if it is real.

Check source images for provenance before publishing.

Verify whether viral content carries a watermark trail.

Check suspicious images from social feeds.

See an image that looks too good to be true? Check it.

●How it works

Three steps. One result.

01

Upload or paste a URL

JPG, PNG or WebP.

02

Watermark + AI check

SynthID, C2PA and EXIF are read. If nothing is found, AI detection runs.

03

Clear result

Watermark status, AI likelihood and the signals behind it.

●Integration

Three ways in.
Start with the web app.

Scan in the web app or Chrome extension today. The REST API and the MCP server for AI assistants are in early access for images. Same detectors, same result.

Web app

Available

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

witness.vision/scan
Page media● Scan
uploaded_image.png · AI-generated · 0.94

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
uploaded_image.png · AI-generated · 0.94

API

Early access

Send an image by file or URL, get structured JSON back: verdict, confidence and provenance signals. Read the docs

POST /api/v1/scan
curl https://witness.vision/api/v1/scan \
  -H "Authorization: Bearer $WITNESS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://…/uploaded_image.png"}'

→ 200 OK · 412ms
verdict: Likely AI · 0.94

●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 and face-swapped video 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

What is SynthID?

An invisible watermark from Google DeepMind, embedded in AI-generated images, audio, video, and text. Over 100 billion items watermarked.

Does no SynthID mean it is real?

No. Most AI generators do not embed SynthID. Witness runs AI detection to catch content with no watermark.

Is the SynthID check free?

Yes. Upload any image for a free SynthID and AI check. No account required.

What about other watermarks?

Witness also reads C2PA Content Credentials from OpenAI, Adobe Firefly, and other adopters.