SynthID Detector

What it is

SynthID Detector is a free web tool hosted by Google at synthid.com. Upload an image, video, or audio file and it reports whether the file carries a SynthID watermark — an invisible machine-readable signal embedded at generation time by participating AI models. Google opened the detector to everyone on October 7, 2026, after a testing period with journalists, media professionals, and researchers that began at Google I/O 2025.

How it works

SynthID watermarks are embedded directly into AI-generated content by the models themselves. The detector looks for that specific signal. Google's Nano Banana, Veo, and Lyria models, along with generation-capable tools such as Gemini, Flow, ProducerAI, and Vids, watermark their output with SynthID; OpenAI, Nvidia, and Kakao also support the standard, and Apple is said to be adding support. Google says the service already handles about 1 million verification requests per day.

What to keep in mind

The detector is a watermark checker, not a general AI detector: it can only identify media that uses SynthID technology. A clean result does not prove a file is human-made — the watermark may have been stripped by editing, or the file may come from a model outside the SynthID ecosystem. It also cannot distinguish AI-created media from AI-edited media. Sign-in is required, uploads are deleted immediately after processing, and automated or bulk submissions are not allowed.