AI Watermark Center
Gemini research

Gemini Content Credentials

Where Gemini Apps and documented Gemini API models attach C2PA Content Credentials, what absence means, and which formats AI Watermark Center can inspect locally.

Published
Last verified
Review
Reviewed against primary sources

Content Credentials are C2PA provenance metadata. SynthID is an imperceptible watermark in the media itself. They can coexist. Finding one does not prove the other, and missing C2PA does not mean SynthID is missing.

Where Gemini Apps documentation establishes credentials

Gemini Apps Help states that Gemini Apps include Content Credentials (C2PA) metadata about origin for AI-generated or edited media. That statement is for Gemini Apps (web and mobile), not automatically every Google generative API or product.

Developer-surface C2PA

The Gemini API model card for Nano Banana 2 Lite currently documents “SynthID (Always On) + C2PA watermarking.” That is a model-card claim for gemini-3.1-flash-lite-image. It is not a licence to assert C2PA on every Nano Banana version.

What credentials can contain

Gemini’s verification help says compatible Content Credentials can summarise media composition, edit history, and whether AI was used, and can name the company that signed the information (for example Google LLC). Credentials do not, by themselves, prove a file is or is not AI-generated in a forensic sense.

What stripping or absence means

Screenshots, some social exports, and re-encodes can drop manifests. Gemini Apps Help also notes that Apps do not support remotely stored third-party credentials. Absence of embedded C2PA is not absence of SynthID and is not proof the file was not generated by Google AI.

What AI Watermark Center can inspect

Embedded manifests in JPEG, PNG, and WebP. Soft bindings and cloud recovery are not performed. C2PA inspection does not detect SynthID.

Inspect Content Credentials

Sources

  1. Manage watermark settings in Gemini Apps — Gemini Apps Help

    Accessed August 16, 2026.

    Current Gemini Apps visible-watermark toggle is Apps-only. India, South Korea, and Vietnam restrict the toggle to AI Ultra; work/school accounts cannot turn it off. The setting does not affect SynthID or Content Credentials.

  2. Verify AI-generated images, videos, and audio — Gemini Apps Help

    Accessed August 16, 2026.

    Gemini user-facing verification for image, video, and audio. SynthID identification is Google AI only; Content Credentials inspection is a separate layer.

  3. Gemini 3.1 Flash Lite Image — Google AI for Developers

    Accessed August 16, 2026.

    Nano Banana 2 Lite (gemini-3.1-flash-lite-image): SynthID always on plus C2PA watermarking. Scope is this API model card, not every Google consumer surface.

In this cluster