| What it does | Deepfake Detection Backed by Forensic Evidence
| Free AI detector with published error rates
|
|---|
| Stage | Startup
| Not given
|
|---|
| Founded | 2024
| Not given
|
|---|
| Based in | NL
| IT
|
|---|
| Pricing model | Contact for pricing
| Free
|
|---|
| Pricing | Not given
| No payment required. Free tier allows 10 certification requests per day per IP.
|
|---|
| Key features | - Multi-layer forensic analysis examining visual inconsistencies, facial behaviour, audio anomalies, metadata, and traces of AI generation
- Facial movement and expression analysis to identify signs of manipulation
- Suspicious region pinpointing with visual indicators in images, videos and audio
- Metadata and provenance inspection to identify inconsistencies
- Explainable results and forensic reports for decision-making and legal proceedings
- Flexible deployment options including cloud, on-premises, containerised and air-gapped setups
- API and SDK integration into existing systems
- Landmarking analysis detecting inconsistencies in facial features and face-to-background alignment
- Behavioral signal analysis tracking blinking, breathing and emotional cues to confirm liveness
- Cross-modality checks aligning and comparing audio and video streams to expose manipulation
| - Calibrated probability scores with published error rates
- Inconclusive verdicts for borderline cases
- Minimum 150 word requirement
- Content Credentials (C2PA) file checking
- Document metadata analysis
- Free human-text certification with downloadable PDF badge
- No signup or account required
- Private processing with no data storage
|
|---|
| What makes it different | - Forensic evidence-backed results with explainable indicators instead of guesswork
- Research-grade technology backed by Rabobank and showcased at major tech events
- Supports investigation, intelligence, law enforcement and legal workflows with evidence-ready outputs
- Multimodal detection across video, audio, image and text with unmatched precision
| - Published error rates with raw counts and confidence intervals
- Designed to minimize false accusations rather than maximize detections
- Measures ESL (non-native English) writer accuracy separately
- Transparent verdicts: reports inconclusive when unsure instead of guessing
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 5 ● no change since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 4 | 2 |
|---|
| Citation Flow (Majestic) | 8 | 13 |
|---|
| Referring domains (Majestic) | 30 | 1 |
|---|
Cyberette
Cobalynx