SynthID

Watermarking and detection for AI generated images, audio, video and text from Google models.

Made by GoogleDeepfake detection and provenance

Visit deepmind.google

About SynthID

SynthID is Google's watermarking tool, designed specifically for AI-generated content. It is intended to help users identify AI-generated or altered content and foster transparency and trust in generative AI.

Google launched the SynthID Detector, a verification portal, in 2025 to verify whether a piece of content was watermarked with Google SynthID. The SynthID Detector allows anyone to check if an image, video, or audio file was made with AI from Google or partners including OpenAI, NVIDIA, Kakao, and soon, Apple.

Drafted from deepmind.google · not yet confirmed by Google

How it works

SynthID embeds an imperceptible watermark into content generated by Google's models (Imagen, Veo, Lyria, Gemini text) and provides a detector that can tell whether a piece of content carries it. The text watermarking is open sourced. It complements C2PA content credentials: credentials record provenance in metadata, SynthID survives metadata stripping.

Reviews

Be the first to review it

Anonymous
Would you use it again?

Signed as your field and level, never your name.

Know a team weighing SynthID? Send them this page.