Google Announces SynthID Detector That Can Identify Gemini-Generated Content at Google I/O 2025

Google I/O 2025 keynote session on Tuesday was focused on new artificial intelligence (AI) updates and features. Alongside, the Mountain View-based tech giant also introduced a new tool to bring more transparency when it comes to AI-generated content. Dubbed SynthID Detector, it is an under-testing verification portal which can detect and identify multimodal AI content made using the company's AI models. The technology can identify audio, video, image, and text, allowing individuals to easily assess if a piece of content is human-made or synthetic.

Google Tests SynthID Detector Verification Platform

The company first unveiled SynthID in 2023 as a technology that can add an imperceptible watermark into content that cannot be removed or tampered with. In 2024, the company open-sourced the text watermarking technology to businesses and developers. The invisible watermark shows up when analysed using special software. Google is now testing a verification portal dubbed SynthID Detector that will allow individuals to quickly check if a media is generated using AI or not.

In a blog post, the tech giant said the portal provides transparency “in a rapidly evolving landscape of generative media.” With Veo 3 and Imagen 4 AI models that can generate hyperrealistic images and videos, the risk of deepfakes has also increased significantly.

While measures such as the Coalition for Content Provenance and Authenticity (C2PA) standard have offered a way for AI companies to highlight AI-generated content, they are not completely tamper-proof. Advanced watermarking technologies enable users and institutions to protect themselves from misinformation and synthetic abusive content.

The portal is straightforward to use, Google explains. Users can upload media they suspect to have been generated using Google's AI tool and SynthID Detector then scans the uploaded media and detects any SynthID watermark. Afterwards, it shares the results, and if a watermark is detected, it highlights which part of the content is likely to be AI-generated. Notably, the tool does not work with non-Google AI products.

One of the biggest advantages of SynthID is that the imperceptible watermark does not compromise the quality of the media, and at the same time, it is not possible to remove or alter it. Currently, Google is rolling out the portal to early testers, and it plans to make it available more broadly later this year. Journalists, media professionals and researchers can join the waitlist to gain early access to the SynthID Detector.