SynthID Checker: How to Check Google's AI Watermark

Since 2024, Google DeepMind has been rolling out SynthID, an invisible digital watermark added to content generated by its AI models. Imperceptible to the eye and ear but detectable by a dedicated tool, it aims to answer a question that has become central: was this text, image or video made by artificial intelligence? As Google embeds SynthID by default across its models, the term is climbing in search. This guide explains what SynthID actually detects, its limits, and why detecting AI is not the same as certifying that a real photo is authentic.

Short answer — how to check for SynthID in 2026:

Gemini app (free, public): upload the image, video or audio file and ask "Was this created with Google AI?". Gemini checks for the SynthID watermark and tells you what it found.
OpenAI's verification tool (openai.com/research/verify): for images made with ChatGPT or the OpenAI API, which carry SynthID and C2PA Content Credentials since May 2026.
Google's SynthID Detector portal: the most detailed tool, but still rolled out through a waitlist — journalists, media professionals and researchers first.

Keep in mind: "no SynthID detected" only means the file was not marked by a participating model. It never proves that a photo is real.

What is SynthID?

SynthID is a watermarking technology built by Google DeepMind. The moment a Google model generates content, SynthID embeds an imperceptible signal directly into the data — a tiny change to an image's pixels, a sound's frequencies or a text's word choices. The result looks identical to a human, but a trained detector can later recognise the signature and report that the content carries a SynthID watermark.

Unlike metadata (easily stripped) or a visible logo (easily cropped out), the watermark is woven into the content itself. Google says it survives many common transformations: cropping, adding filters, compression, or changing a video's frame rate. According to Google DeepMind, more than 10 billion pieces of content have already been watermarked with SynthID.

What SynthID detects (and across which content)

Originally limited to images, SynthID now covers the four main content types generated by Google's models:

Images — via the Imagen generator.
Video — via Veo, Google's video generation model.
Audio — via Lyria (generated music and sound).
Text — via Gemini, by subtly steering word choice in a detectable way.

To check content, Google built the SynthID Detector, a portal that analyses an uploaded file and flags the likely presence of a SynthID watermark, indicating which parts of the content are affected. The portal is still rolled out through a waitlist; for everyone else, Google has made the same check available in the Gemini app since November 2025 — which is what brought "SynthID check" into everyday language.

An invisible cryptographic watermark being embedded into an AI-generated image at creation time — The watermark is embedded at generation time, straight into the pixels — invisible to humans, readable by the detector.

The limits: what SynthID does not detect

Only Google's ecosystem (and a few partners)

This is the decisive limitation. SynthID only spots content produced by models that embed the watermark: Google's own (Gemini, Imagen, Veo, Lyria) and a growing number of partners — most notably OpenAI, which has embedded SynthID in images generated with ChatGPT and its API since May 2026. An image from Midjourney, Stable Diffusion or Adobe Firefly carries no SynthID watermark — the detector will return "no detection" even though the image is genuinely AI-generated. SynthID therefore sees only a fraction of the synthetic content in circulation.

The watermark can erode

Robustness has limits. Heavy transformations — intensive editing, strong re-compression, screenshots, and for text, translation or a full rewrite — can weaken or erase the watermark. Text watermarking is the most fragile: a few rewordings are often enough to collapse the detector's confidence. The output is expressed as a probability, not a binary certainty.

Absence of a watermark proves nothing

The corollary of the two points above: a "no SynthID watermark" result does not mean "authentic content." It could be a real photo… or an image from a non-participating model, or content whose watermark was destroyed. SynthID can confirm an AI origin; it cannot rule it out.

Detecting AI ≠ certifying a real photo

This is the most important nuance, and the most misunderstood. SynthID answers "was this content made by an AI?". It does not answer the opposite question — often the only one that matters to an insurer, a court or a client: "is this real photo authentic, taken where and when claimed?".

These are opposite problems. The first tries to unmask the synthetic. The second tries to prove the real — a capture's provenance, its timestamp, its integrity. A SynthID watermark on a generated image says nothing about the reliability of a damage photo taken by a policyholder; and a real photo, by definition, carries no SynthID watermark.

On one side a magnifier searches an AI image for a watermark, on the other a real photo is sealed with a shield — Two opposite logics: spotting the AI-generated fake (detection) versus proving a real capture is authentic (certification).

SynthID, C2PA, capture-time certification: complementary logics

Three approaches coexist, and they do not replace one another:

SynthID (watermark) — marks AI-generated content at the source. Useful for flagging the synthetic, limited to the ecosystem that emits it.
C2PA / Content Credentials — an open standard (Adobe, Microsoft, the BBC…) that attaches a signed "where this file came from" history. Useful when the device or software actually writes it.
Capture-time certification — seals the authenticity of a real photo or video at the moment it is taken, with a verifiable cryptographic fingerprint.

That third path is the one Truth-Check takes: the photo is captured straight from the device sensor inside the app, then the image, its metadata, its location and a SHA-256 hash are sealed. Any later modification breaks the hash, and anyone can verify the certificate publicly. Where SynthID tries to spot the fake after the fact, certification proves the real at capture — a positive, binary proof that does not depend on knowing which generator did (or did not) mark the content.

Should you rely on SynthID to verify evidence?

SynthID is a real and welcome advance against AI-generated disinformation. But to establish that a photo or video is reliable evidence, it has three blind spots: it is proprietary (controlled by Google), it does not cover content outside its ecosystem, and above all it does not certify the authenticity of a real capture — so it does not replace a certificate. A watermark can, at best, reveal that content is artificial. Proving that content is authentic remains a separate task. To go further, see our guides on how to detect an AI-generated photo and the 7 tools to verify a photo's authenticity.

How to check an image for SynthID, step by step

There is no open, stand-alone "SynthID checker" website. In 2026, the practical entry point is the Gemini app, which runs the SynthID check for you. Google's dedicated SynthID Detector portal — which highlights the watermarked areas of a file — is still reserved for waitlisted testers.

In practice, a "SynthID check" in Gemini goes like this:

Open the Gemini app (web, Android or iOS).
Upload the file to check — one image, video or audio file at a time, up to 100 MB.
Ask: "Was this created with Google AI?" or "Is this AI-generated?"
Read the answer. If a watermark is detected, all or part of the file was created or edited with Google AI. If not, the file simply was not marked by Google's tools — it may still come from another generator.

Gemini currently only recognises content made with Google's own AI tools. For an image you suspect comes from ChatGPT, use OpenAI's verification tool, which looks for OpenAI's SynthID watermark and its C2PA Content Credentials.

SynthID answers only one narrow question. To look at other signals in a photo — EXIF metadata, file integrity, visual traces of editing or AI generation — you can run it through our free photo verification tool. It does not read SynthID, and like any detector its score is a clue, not proof.

Three caveats before relying on a SynthID checker: it only recognises content marked by Google's models and its partners (a Midjourney or Stable Diffusion image will come back "no detection" even though it is AI-generated); the watermark can be weakened by heavy editing or strong re-compression; and above all, a "no watermark" result does not prove that content is authentic. Checking for AI and proving that a real photo is authentic remain two separate tasks.

FAQ

How do I do a "SynthID check"?

The simplest way is the Gemini app: upload your image, video or audio file and ask "Was this created with Google AI?". Gemini checks for the SynthID watermark and reports what it found. It only covers content made with Google's AI tools; Google's more detailed SynthID Detector portal is still waitlist-only.

Is there a free SynthID checker?

Yes: the Gemini app runs the SynthID check for free, and OpenAI offers a free verification tool for images from ChatGPT and its API. Neither can detect content from models that do not embed SynthID (Midjourney, Stable Diffusion, Firefly…), and the absence of a watermark never proves that content is authentic.

Is SynthID 100% reliable?

No. It detects content marked by participating models with good confidence, but the result is probabilistic and the watermark can be weakened by heavy editing, strong re-compression, or — for text — a rewrite or translation.

Can SynthID detect a Midjourney or DALL·E image?

Midjourney: no — it does not embed SynthID. ChatGPT: yes for recent images — since May 2026, OpenAI embeds SynthID in images generated with ChatGPT and its API (older DALL·E images carry none). To check a ChatGPT image, use OpenAI's verification tool: the Gemini app only recognises content made with Google's own tools.

Does a SynthID watermark prove a photo is authentic?

No, it's the opposite: a SynthID watermark indicates that content was generated by an AI. Proving that a real photo is authentic is a matter of provenance and capture-time certification, not AI detection.

Does SynthID replace an authenticity certificate?

No. SynthID marks synthetic content at the source; a certificate proves the integrity and origin of a real capture. The two approaches are complementary and answer different needs.