SynthID Detector can check media to see if it was generated with Google's AI tools

Google originally launched SynthID, its digital watermark for AI-generated content, as a way to detect whether an image was created using the company's Imagen model in 2023. Now, at Google I/O 2025, the company is introducing a public-facing tool called SynthID Detector that claims to detect those watermarks in just about anything you upload.

SynthID Detector will be available as a web portal where you can upload images, video, audio and text to be scanned. Once uploaded, SynthID Detector Google claims the portal can tell you whether your upload contains AI-generated material and even "highlight specific portions of the content most likely to be watermarked." For audio, the tool is supposed to be able to identify a specific portion of a track that contains the watermark, too.

A gif showing how SynthID Detector scans media.
Google

SynthID was designed to mark content from Google's models but Google hopes other companies will adopt the watermark for their own AI output. An open source version of SynthID is already available for text watermarking, and as part of the rollout of SynthID Detector, Google is partnering with NVIDIA to mark media its NVIDIA Cosmos model generates. SynthID Detector won't be the only tool that can spot Google's watermark, either. The company says GetReal Security will also be able to verify if media contains SynthID. 

Considering the sheer number of ways Google hopes people will using AI to create images, video, text and audio, from the Audio Overviews in NotebookLM to short films made with its new Flow tool, it makes sense that it would offer a way to know if any of those things are real. Until models from one company produces the vast majority of content or a digital watermark reaches widespread adoption, though, a tool like SynthID Detector can only be so useful.

Journalists, researchers and developers can join a waitlist to try SynthID Detector through Google's online form.

This article originally appeared on Engadget at https://www.engadget.com/ai/synthid-detector-can-check-media-to-see-if-it-was-generated-with-googles-ai-tools-194002070.html?src=rss https://www.engadget.com/ai/synthid-detector-can-check-media-to-see-if-it-was-generated-with-googles-ai-tools-194002070.html?src=rss
Erstellt 1mo | 20.05.2025, 21:10:18


Melden Sie sich an, um einen Kommentar hinzuzufügen

Andere Beiträge in dieser Gruppe

Perplexity's AI-powered browser opens up to select Windows users

Perplexity is planning to open up its Comet browser that's powered by "agentic search" to Windows users, according to the company's CEO. Aravind Srinivas

22.06.2025, 19:40:05 | Engadget
The Blood of Dawnwalker developers share a look at gameplay from the upcoming vampire fantasy RPG

One of the games that really caught my eye during the

22.06.2025, 19:40:04 | Engadget
How to buy the Nintendo Switch 2: Latest stock updates at Target, Best Buy, Walmart and more

The Nintendo Switch 2 has been available in the US for more than two weeks — but good luck finding one. While

22.06.2025, 17:20:09 | Engadget
Texas will require permits for self-driving cars starting in September

Starting September 1, fully autonomous cars will require a permit to operate in Texas. This new restriction comes after the state's governor, Greg Abbott, signed into law the

22.06.2025, 17:20:06 | Engadget
Tesla's inaugural Robotaxi rides will have a human 'safety monitor' on board

A select few will soon get to experience Tesla's robotaxi service for the first time, but they won't be alone in the car. The company plans to launch its fully autonomous ride-hailing service in Au

21.06.2025, 18:10:16 | Engadget