Skip to content
GeminiDetect
English

What is SynthID?

By Yang Zheng · Updated

SynthID is Google DeepMind's invisible watermark for AI-generated content. It marks images, video, audio and text made with Google AI, and Google's public SynthID Detector, open to everyone since 2026-10-07, reads it for images, video and audio only.

How it works by media type

What a missing mark does and does not mean

No watermark found means the checker did not find one. It does not show a human made the content, because other AI tools can produce images and text without SynthID. It is also not proof either way for edited files.

Checking images

Pictures from Google tools are the most common SynthID question. For an image, use an image detector that does not depend on a watermark, and check the file's embedded metadata. The Gemini detector facts sheet lists what Google's own tools do and do not cover.

Checking text

For text, use GeminiDetect to see an AI verdict and Gemini style similarity. It does not read SynthID. Its engine, Veread, comes from Fileverity, and the best Gemini AI detectors page compares it with other tools.

Sources: Google DeepMind SynthID pages; Google blog, 2026-10-07; Gemini Apps Help.

Questions and answers

What is SynthID?

SynthID is Google DeepMind's watermarking technology for AI-generated content. It embeds an invisible signal in content made by Google AI and, for some partners, their tools.

Does SynthID work on text?

Google says it watermarks text generated in the Gemini app and web experience, but its public detector does not check text. The watermark is less effective on factual prompts and weakens after heavy rewriting.

How do I check if an image is AI?

A SynthID check only covers content made with Google AI. For anything else you need an image detector that does not depend on a watermark, and the photo's embedded metadata shows what the file declares.