AI Watermark Center
OpenAI research

OpenAI SynthID

Where OpenAI currently documents SynthID on supported generated images and audio, how it relates to C2PA, and why AI Watermark Center cannot detect it.

Published
Last verified
Review
Reviewed against primary sources

This page is about where OpenAI currently documents SynthID, not a general “what is SynthID?” explainer. For the technology itself, use the separate guide.

Images

OpenAI Help Center states that supported images generated with ChatGPT, Codex, and the OpenAI API include SynthID watermarks as well as C2PA metadata. SynthID is described as a signal in the content that may persist through some edits after metadata is gone. That complementary role is why OpenAI presents a layered approach. It is still not a visible logo.

Audio

OpenAI’s 31 July 2026 provenance update states that supported generated audio, including through ChatGPT and the OpenAI API, includes SynthID, and that public verification was expanded to supported audio. This site has no audio inspector. Audio is context for OpenAI’s SynthID adoption, not an audio SEO cluster.

Relationship with C2PA

C2PA is structured, signed metadata. SynthID is an invisible watermark in the media. They can coexist. Finding one does not prove the other. Missing C2PA does not mean SynthID is missing. AI Watermark Center’s image inspector reads embedded C2PA; it does not detect SynthID. AI Watermark Center does not currently detect SynthID.

Public verification

OpenAI Verify and the Content Provenance API can look for a supported OpenAI SynthID signal on supported files. Those results are provider-verified. OpenAI documents a Content Provenance API for supported image and audio files. AI Watermark Center does not integrate that API and does not upload user files to OpenAI.

Official OpenAI verification (opens in a new tab)External provider tool

Read the generic SynthID guide

Sources

  1. Provenance signals (Content Credentials, SynthID) in OpenAI-generated content — OpenAI Help Center

    Accessed August 17, 2026.

    Primary source for current OpenAI image C2PA + SynthID on supported ChatGPT, Codex, and API outputs; audio SynthID; prompt-requested visible disclosure; and openai.com/verify. Visible marks are separate from embedded signals.

  2. Advancing content provenance for a safer, more transparent AI ecosystem — OpenAI

    Published July 31, 2026. Accessed August 17, 2026.

    31 July 2026 update: supported audio SynthID, audio on the public verifier, and verification API access. Historical context for layered C2PA + SynthID; current product scope follows the Help Center.

  3. Verify — OpenAI

    Accessed August 17, 2026.

    Public verification surface referenced by OpenAI Help Center for supported image and audio provenance signals (C2PA and/or SynthID). External provider tool — not an AI Watermark Center feature.

  4. Content provenance — OpenAI API documentation

    Accessed August 17, 2026.

    Content Provenance API (also referenced as OPENAI-API-PROV-001 in Phase 7 notes). Images: C2PA + SynthID. Audio: SynthID. Documents not_detected semantics. Public/documented; not integrated by AI Watermark Center.

In this cluster