AI Video Detector logo AI Video Detector

AI video evidence

Deepfake Video Detector

Check public social videos for deepfake and AI-manipulation signals with a cautious evidence report. Use it as a first-pass screening aid, not proof.

Important: Do not use automated results alone to accuse, harass, shame, or target any person.
Check video linkSee report limits

AI video check

Check a public link or upload the original video

Public TikTok and X/Twitter links are in beta when accessible. Instagram and YouTube links may return limited link scans. Upload the original file for the most reliable frame, motion, and timeline analysis.

YouTubeTikTokInstagramX / TwitterUpload

Option 1

Fastest

Best-effort for supported public social video URLs. If public media is unavailable, upload the original video for deeper analysis.

Option 2

Deeper scan

Use upload when you need the strongest available frame, motion, and timeline analysis.

By clicking Check video link, you confirm you have the right to submit this video link for analysis and understand results are likelihood-based, not proof.

Estimated credits depend on video size and duration. Detected platform: Unknown.

Live analysis process

Professional evidence workflow

Follow the analysis pipeline below the detector. Progress is stage-based and evidence scores are only shown for signals that can be checked.

Likelihood-based · not proof
  1. 1Input
  2. 2Access
  3. 3Media
  4. 4Queue
  5. 5Analyze
  6. 6Report

Check progress

Step 0 of 6

How the check works

Paste a public video link or upload a video you have the right to analyze. We show what can be checked, what may be limited, and how to read the result.

Ready when you are · stage-based progress

Analysis timeline

Evidence pipeline progress

Each stage shows local progress. Timing is stage-based and depends on media access and plan limits.

Stage-based
  1. 1

    Checking input

    Validate the URL, file, consent, and supported video source.

    Running

    35% · Running

  2. 2

    Checking access

    Run security checks and see what media can be reached safely.

    Pending

    0% · Pending

  3. 3

    Preparing media

    Upload, resolve, or prepare accessible video signals for analysis.

    Pending

    0% · Pending

  4. 4

    Queue

    Place the scan in the analyzer queue with plan-based priority.

    Pending

    0% · Pending

  5. 5

    Extracting signals

    Read frames, motion, metadata, compression, and audio/video signals when available.

    Pending

    0% · Pending

  6. 6

    Building report

    Assemble likelihood, confidence, limitations, and recommendations.

    Pending

    0% · Pending

Signal checks

Evidence signal readiness

During analysis, this panel shows process status only. The formal six signal groups appear in the completed result below.

Process status

Source/media access

Waiting for the analyzer to confirm source and media access.

Pending

Pending

Visual artifact signals

Numeric scores appear only after visual evidence is actually sampled.

Pending

Pending

Motion/temporal consistency

Numeric scores appear only after temporal checks complete.

Pending

Pending

Compression/encoding patterns

Numeric scores appear only after compression and encoding checks complete.

Pending

Pending

Audio-video consistency

Numeric scores appear only when audio/video evidence is available.

Pending

Pending

Source detail signals

Source detail checks appear only when media or source metadata is available.

Pending

Pending

What is a deepfake video?

A deepfake is a video that changes or imitates a person’s face, voice, body movement, or actions in a synthetic or misleading way. Some deepfakes are obvious. Others are subtle, short, compressed, or mixed with real footage.

Not every AI-generated video is a deepfake. A fully synthetic animation, an AI-made product clip, or a stylized creative video may be AI-generated without pretending to show a real person doing something.

How AI Video Detector checks for deepfake signals

  • Face shape or texture changes.
  • Eye, head movement, and visual motion issues.
  • Hand, object, and background artifacts.
  • Flicker, warping, or unnatural movement between frames.
  • Audio-video consistency signals when readable audio is available.
  • Signs that the clip has been compressed, edited, or reposted.

Safe use policy

  • Use the report for media literacy, source checking, and first-pass review.
  • Do not harass, threaten, shame, or dox someone.
  • Do not claim a person committed fraud or misconduct.
  • Do not identify or verify a private person.
  • Do not handle non-consensual intimate content.
  • Do not publish the report as final proof.

FAQ

Questions this page answers

What deepfake clues does this page focus on?

It focuses on face, hand, motion, mouth-sync, background, texture, and source-limit clues that may appear in manipulated video.

Is every AI-generated video a deepfake?

No. A synthetic product clip or animation may be AI-generated without impersonating a real person.

What should I do with a high-risk deepfake result?

Pause sharing, compare original sources, and request human review before taking action.