AI video detectorIs this video AI?

Drop a video to check if it was made with AI.

AI video detector

Sora, Veo, Kling, Seedance and more

What it checks

Content CredentialsC2PA labels in the container
Generator fingerprintsEncoder and tool tags
Camera dataPhone and camera tags
Visual inspectionFaces and motion across frames

Private. The file is checked on your device.

Drop a video to get a verdict

It names the AI that made it when the file says so, and checks the pixels when it does not.

AI

Sora

Content Credentials in the file

AI

Veo

Frames that drift and morph

AI

Kling

Tool tags and motion

Real

Phone footage

Camera tags in the file

  • Free, no sign-up
  • Images and video
  • Names the AI that made it
  • Private: files stay on your device

Open the full detector

In short

Drop a video to check if it was made with AI. Gireta reads the Content Credentials (C2PA) that Sora writes into its files, the encoder and camera tags phones and generators leave, then compares four frames for the tells of Sora, Veo, Kling and Seedance: faces that drift, objects that morph and physics that does not hold.

How the video check works

  1. 1

    Content Credentials in the container

    MP4 and MOV files can carry a C2PA manifest in a dedicated box. Sora writes one; so do Adobe tools and some cameras. We read it in your browser.

  2. 2

    Encoder and camera tags

    Phones record their make, model and software in the file. Generators and editors often leave their own encoder name. Re-encoded downloads usually carry neither.

  3. 3

    Four frames, compared

    We take four frames from evenly spaced points and inspect them side by side: faces and objects that change identity, limbs that morph, text that melts and motion that defies physics.

  4. 4

    A verdict with its evidence

    Content Credentials confirm it outright. Otherwise the frames and file data are weighed together, and the verdict comes with a confidence level and everything it found.

What AI video generators leave behind

GeneratorLabelsWhat Gireta reads
Sora (OpenAI)A visible moving watermark and C2PA Content CredentialsThe C2PA manifest, then the frames
Veo (Google)A SynthID watermark in the framesThe frames; SynthID needs Google's detector
Kling, Seedance, Hailuo, Runway, Pika, LumaUsually a visible logo on free plans; little or no metadataEncoder tags when present, then the frames
Phone and camera footageMake, model and software tags; some cameras sign with C2PACamera tags and any manifest

Downloading from TikTok, Instagram or X re-encodes the video and strips its metadata, and visible watermarks are easy to crop. A clean file proves nothing either way.

Signs a video was made with AI

  • Faces, clothes or tattoos that change between shots of the same person
  • Hands and props that merge, multiply or pass through each other
  • Text on signs and screens that shifts or reads as nonsense
  • Background people who walk in loops or melt into the scenery
  • A floating, too-smooth camera with no shake, even when handheld
  • Shadows and reflections that do not follow the action
  • Clips that are exactly 5, 8 or 10 seconds long with no natural cut

Why Gireta catches what single-model detectors miss

Most detectors run one classifier over the pixels and hand back a score. Gireta starts where the proof is: the signatures AI tools embed in their own files. When ChatGPT, Gemini, Firefly, Sora or Stable Diffusion have labelled an image, Gireta reads that label, confirms the verdict and names the tool.

When the labels have been stripped, four more layers run: generator fingerprints in the file, camera data, a close visual inspection of hands, text, light and texture, and forensic views of the pixels. The verdict comes with the evidence behind it, so you can show your work.

And it all runs in your browser, so you can check sensitive images without uploading them anywhere.

More ways to check

Images

AI image detectorCheck if an image is AI-generated, free. Reads Content Credentials, IPTC labels and generator settings from ChatGPT, Gemini, Midjourney and Stable Diffusion, then inspects the pixels.How to tell if an image is AI generatedTen ways to tell if an image is AI-generated, from the strongest evidence (Content Credentials, metadata, SynthID) to the visual tells in hands, text and light.Content Credentials (C2PA) checkerCheck an image's Content Credentials (C2PA) and IPTC source type online, free. See if it was made or edited with AI, and which tool made it.AI image metadata checkerSee an image's hidden metadata: the Stable Diffusion or ComfyUI prompt, EXIF camera data, XMP and C2PA. Free, in your browser, with error level analysis.ChatGPT image detectorCheck if an image was made with ChatGPT, GPT Image or DALL·E. Reads OpenAI's Content Credentials and inspects the image, free and private.Gemini and Nano Banana image detectorCheck if an image was made with Google Gemini, Nano Banana or Imagen. Reads C2PA and IPTC labels in your browser and explains SynthID.Midjourney detectorCheck if an image was made with Midjourney. Reads IPTC labels and prompt text, then inspects the image for Midjourney's look. Free and private.Stable Diffusion detectorCheck if an image was made with Stable Diffusion or SDXL and read its prompt, seed, sampler and model from the file. Works with Automatic1111, Forge, Fooocus and ComfyUI.Flux image detectorCheck if an image was made with Flux. Reads ComfyUI and Forge workflows from the file, names the model, and inspects the image. Free and private.Grok image detectorCheck if an image was made with Grok on X. Reads any embedded labels and inspects the image for the tells of AI generation. Free and private.

Make AI video that stands out

Gireta puts Seedance, Kling, Veo and every top video model in one studio, with one balance.

Start creating

Questions

How can you tell if a video is AI-generated?

Check for Content Credentials first: Sora writes them into the file, and Gireta reads them in a second. Then look across frames for faces and objects that change, text that melts and physics that fails. Google's SynthID Detector reads the watermark in Veo videos.

Can it detect Sora videos?

Yes, when the file still carries its C2PA manifest. Re-uploaded copies lose it, so the visual check carries the result, and the moving Sora watermark is a strong clue when it has not been cropped.

Is the Gireta AI video detector free?

Yes, with no sign-up. The visual check is rate limited per visitor to keep it free.

Do you upload my video?

No. The file is read in your browser. Only four small frames are sent for the visual check, then discarded.

How long can the video be?

Any length. We read the metadata at the start and end of the file and take four frames, so long files are checked as quickly as short ones.

Can it detect deepfakes?

It catches fully generated video and the frame-to-frame glitches generators leave behind, such as faces and objects that change identity between frames.

Sources

Last updated October 19, 2026.