SynthID Detector — an innovative tool for recognizing AI-generated content

Sure! Here’s the rewritten content with the requested adjustments:

—

Advances in generative AI are enabling individuals to create content in entirely new ways — from text to high-quality audio, images, and videos. As these capabilities evolve and become more accessible, questions of authenticity, context, and verification arise.

Today, we’re announcing the SynthID Detector, a verification portal designed to quickly and efficiently identify AI-generated content created with Google AI. This portal consolidates detection capabilities across different media types and provides essential transparency in the fast-changing landscape of generative media. It also highlights which parts of the content are most likely to have been watermarked with SynthID.

When we launched SynthID — a cutting-edge tool that embeds imperceptible watermarks for identifying AI-generated content — our goal was to deliver innovative technical solutions to help reduce misinformation and misattribution. SynthID not only maintains the quality of the content but also acts as a resilient watermark that remains detectable even after sharing or various modifications. Originally focused on AI-generated imagery, we’ve now expanded SynthID to encompass AI-generated text, audio, and video content, including outputs from our Gemini, Imagen, Lyria, and Veo models.

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 text created using Google’s AI tools, the portal scans the media for a SynthID watermark. If a watermark is detected, the portal highlights specific portions of the content that are most likely to be watermarked. For audio, it pinpoints segments where a SynthID watermark is detected, and for images, it indicates areas where a watermark is most likely.

—

Let me know if you need any further adjustments!