Welcome to RealScan, Reality Defender’s web platform for detecting AI-generated or manipulated media across images, videos, audio, and text.
Whether you’re a journalist verifying footage, a trust-and-safety analyst, or a researcher testing detection models, RealScan lets you upload media and get clear, explainable results.
Create or Access Your Account
New to Reality Defender? Create an account at app.realitydefender.ai.
All new users get access to our API and SDK. To import & analyze media directly in the web app, select Upgrade Plan → Analyst, or contact Sales.
Joining an Enterprise account? You’ll receive an email invitation to join. Follow the link to set your password and sign in.
Roles and Permissions
Your access to RealScan is determined by the role assigned by your organization's administrator. There are four RealScan roles:
Role | What you can do |
Owner | Manage plans and billing, manage team members and settings, manage API keys, submit media, and view all scans. |
Admin | Manage team members and API keys, change settings, submit media, and view all scans. |
Contributor | Create API keys, submit media, and view your own scans. |
Viewer | View all scans (read-only). |
Supported Files
RealScan formats & limits (API supports additional formats noted below)
Type | Formats | Max Size | Notes |
Image | jpg, jpeg, png, gif, webp | 50 MB | Use original files; avoid screenshots or heavy compression. See GIF note below. |
Video | mp4, mov | 250 MB or 30 minutes, whichever comes first | Avoid black bars and blurry faces; one fake face can flag the whole clip. |
Audio | flac, wav, mp3, m4a, aac, ogg | 20 MB | Single-speaker only (~ 6 seconds). Noisy or multi-speaker clips may return “N/A.” |
Text | Pasted text, or a .txt, .pdf, .docx, .rtf, .jpg, or .png file | 5 MB per file; up to 900 KB of extracted text | Minimum 200 characters. English input recommended; see language note below. |
Batch uploads: RealScan supports up to 10 files at a time.
GIF files: GIFs are analyzed as a single still image (the first frame). Animation is not analyzed, and results may be less reliable than for other image formats. For best results, upload the original image (jpg or png) or, for animated content, the source video (mp4 or mov).
Language support (text/audio): Production support targets English (all accents). Our methods are language-agnostic and can be extended to other languages on request.
Upload Tips for Best Results
Use the original source file whenever possible.
Avoid additional compression, repeated re-encoding, and screenshots or screen recordings.
Keep faces clear and in focus; avoid extreme crops.
Don’t add black borders (pillarboxing/letterboxing).
For scenery or non-face content, detection is improving continuously; results may vary.
Heavy compression and re-encoding can remove useful detection signals and introduce artifacts that may affect detection accuracy. Results for low-quality media may be incorrect and should not be treated as definitive.
Run Your First Scan
Click Upload Media or drag & drop your file.
Or paste a social link from X (Twitter), YouTube, TikTok, Facebook, or Instagram.
RealScan analyzes your file and displays results when processing completes.
Timing: Processing time varies by file size/quality and system load. During high traffic, scans may queue briefly.
Read Your Results
Every scan includes:
Overall Results Score — a number indicating the likelihood that the content has been manipulated or AI-generated
Final Conclusion — Authentic, Suspicious, or Manipulated, determined by Reality Defender's models and, if enabled, Context and Metadata analysis
Model indicators — visual signals showing which detection models were triggered
For a full explanation of how to interpret your results, see Understanding your Results.
Manage Your Workspace
Your scan history, account settings, and team management are all accessible from the sidebar. For a full overview of the dashboard and navigation, see Navigating the Dashboard.
Privacy & Security
Files are encrypted in transit and at rest on AWS.
Optional delete-after-processing configuration.
We never train our detection models on customer data.
Models focus on signal/artifact analysis (not metadata content).
The platform maintains a range of US/UK/EU certifications and have completed SOC 2 and GDPR certification.
Need Help?
Chat: Send a message to support using the bot in the bottom right corner
Email: support@realitydefender.com
Next Steps
Learn to interpret your results: Understanding your Results
Questions about your plan or access? Contact your Customer Success Manager.