SynthID Detector — a new portal to help identify AI-generated content

Advances in generative AI are making it possible for people to create content in entirely new ways — from text to high quality audio, images and videos. As these capabilities advance and become more broadly available, questions of authenticity, context and verification emerge.

Today we’re announcing SynthID Detector, a verification portal to quickly and efficiently identify AI-generated content made with Google AI. The portal provides detection capabilities across different modalities in one place and provides essential transparency in the rapidly evolving landscape of generative media. It can also highlight which parts of the content are more likely to have been watermarked with SynthID.

When we launched SynthID — a state-of-the-art tool that embeds imperceptible watermarks and enables the identification of AI-generated content — our aim was to provide a suite of novel technical solutions to help minimise misinformation and misattribution.

SynthID not only preserves the content’s quality, it acts as a robust watermark that remains detectable even when the content is shared or undergoes a range of transformations. While originally focused on AI-generated imagery only, we’ve since expanded SynthID to cover AI-generated text, audio and video content, including content generated by our Gemini, Imagen, Lyria and Veo models across Google. Over 10 billion pieces of content have already been watermarked with SynthID.

How SynthID Detector works

When you upload an image, audio track, video or piece of text created using Google's AI tools, the portal will scan the media for a SynthID watermark. If a watermark is detected, the portal will highlight specific portions of the content most likely to be watermarked.

For audio, the portal pinpoints specific segments where a SynthID watermark is detected, and for images, it indicates areas where a watermark is most likely.

Here’s how the SynthID Detector works ¹ :

1. Upload content: Upload an image, audio track, video or piece of text created using Google's AI tools.
2. Scan for watermarks: The portal scans the uploaded media and detects whether the uploaded content, or specific portions of it, contain a SynthID watermark.
3. View results: The portal will present the results and if a SynthID watermark is detected, highlight which parts of the content are more likely to have been watermarked.

We are starting to roll this out to early testers today, before making it available more broadly. Journalists, media professionals and researchers can join our waitlist to gain access to the SynthID Detector.

Expanding the SynthID ecosystem

To help grow a trusted ecosystem we’ve already open sourced SynthID text watermarking, so any developer can build with this technology and incorporate it into their own models.

And earlier this year we took the first step in creating an ecosystem of industry partners to expand the use of the SynthID technology: We partnered with NVIDIA to watermark videos generated by their NVIDIA Cosmos™ preview NIM microservice on build.nvidia.com. This means that more content across the web has SynthID embedded in it, not just content generated by Google.

At the same time, it’s important that other partners will be able to detect when a piece of content has been watermarked with SynthID. That’s why today we’re also announcing our partnership with GetReal Security, the world’s leading content verification platform.

Content transparency remains a complex challenge. To continue to inform and empower people engaging with AI-generated content, we believe it’s vital to continue collaborating with the AI community and broaden access to transparency tools.

The author would like to thank Miguel de Andrés-Clavera and the Google Partner Innovation team for their assistance in developing the SynthID Detector portal.