Detect Sora AI Videos

Objects in Sora video maintain shape too perfectly between frames relative to real-world camera footage. In genuine handheld recordings, micro-vibrations in the camera introduce subtle frame-to-frame position variance. Sora's synthesized camera motion is smooth in a way that real lenses and camera rigs do not produce: there is no handheld shake, no real lens distortion at the periphery, no subtle focus breathing.

Background elements in Sora video show ghosting at frame transitions. When a camera pans, real backgrounds have motion blur that is physically consistent with the pan direction and speed. Sora's background rendering shows temporal blending artifacts at transitions, which you can often spot by stepping through a pan frame by frame.

Sora's physics simulation, while impressive, still renders fluid dynamics, hair, and cloth in identifiable ways. Water behavior is the most reliable signal - Sora-generated water lacks the chaotic turbulence of real fluid dynamics and instead shows a pattern-repeating quality that emerges from learned rather than simulated physics. These are clues to check by eye; FauxLens does not score them one by one.

Sora (OpenAI) uses video diffusion transformers trained on licensed video data. It produces C2PA content credentials by default, which are the most reliable detection signal when intact. At the frame level, Sora exhibits characteristic temporal coherence: objects move too consistently, physics is too smooth, and camera motion lacks organic variation.

Veo 2 (Google DeepMind) was trained on YouTube-scale video data, which means its outputs reflect the visual distribution of consumer video more closely than Sora. This makes Veo 2 videos feel more naturalistic in casual viewing but still leaves temporal artifacts, such as motion that is smoother than real handheld footage. Veo 2 uses a different denoising trajectory than Sora, so its failures look different, though FauxLens checks it the same way as any other clip.

Kling (Kuaishou) was trained primarily on video content with a different regional and stylistic distribution, which creates identifiable visual artifact patterns particularly visible in facial texture rendering and background element treatment. Kling's cloth simulation and hair rendering show characteristic regularities that emerge from its training data. These can show up in single frames even when re-encoding has blurred the motion.

FauxLens reports whether the clip looks AI-generated, with a confidence score, and names a tool only when the file's own credentials or metadata do.

FauxLens reads C2PA credentials as the first step in Sora analysis. If a valid OpenAI C2PA credential is present, the video is definitively identified as Sora-generated with high confidence, regardless of what the video shows.

The complication is that C2PA metadata is fragile. It is stored in the file container, not in the encoded video frames. Re-encoding (which happens automatically when a video is uploaded to Twitter/X, TikTok, Instagram, WhatsApp, or Telegram), strips the C2PA credential from the file. Downloading a Sora video from social media and checking it for C2PA metadata will return nothing, even if the original had the credential intact.

This is where the analysis of the clip itself takes over. Without C2PA metadata, FauxLens judges the clip either from the whole file or from a set of sampled frames, which keeps detection possible on the social media clips most likely to spread as disinformation, though heavy re-encoding lowers confidence.