Drop your image or video anywhere
Our AI video detector automatically detects videos from popular AI generators. No watermarks needed.
"status": "success",
"request": {
"id": "req_fPDJ8fsQGgC1E2Ed8V",
"timestamp": 1709634469.399,
"operations": 24
},
"type": {
"ai_generated": 99%
},
"media": {
"id": "med_fPDJiQzaZR2E193CXb",
"uri": "video.mp4"
}
Synthetic identities and AI-based presentation attacks to bypass KYC checks.
Real-time filters used by romance or investment scammers, or by candidates in hiring processes.
Generating or modifying dashcam footage to misrepresent events.
Fake videos of incidents or surveillance camera to support fraudulent insurance claims.
Face-swaps or nudification tools used to generate abusive videos.
Generation of abusive videos to harass or humiliate individuals.
Deepfake avatars used in live video calls to authorize fraudulent corporate transfers.
AI-generated fake news and deepfakes being spread in media.
Source: Étude de l'Université de Rochester et de l'Université du Kansas
Cette recherche externe a été menée sur 80000 images, comprenant à la fois des images réelles et des images artificielles produites par divers modèles de génération d'images à partir de texte. Ces images étaient nouvelles et par conséquent inconnues des participants testés.
L'article de recherche est disponible ici.
Our Automated AI-generated video detection tool can help you determine the provenance and authenticity of videos.
Sora
Wan
Veo
Kling
Runway
MidJourneyThe detection is based on the pixel content of the video, and therefore works even for videos where meta-data has been stripped and where no watermark is available.
Watermarks and meta-data are not always integrated into AI-generated videos. When users upload a video to popular apps or platforms, the meta-data is automatically stripped.
The Sora, Wan, Veo, Kling, Runway, and MidJourney trademarks and logos are the property of their respective trademark holders. They are not affiliated with Sightengine.
Notre API a été conçue pour et par des développeurs. Copiez-collez quelques lignes de code et le tour sera joué !
curl -X POST 'https://api.sightengine.com/1.0/video/check-sync.json' \
-F 'media=@/path/to/video.mp4' \
-F 'models=genai' \
-F 'api_user={api_user}' -F 'api_secret={api_secret}'
Scalable à l'infini. Modérez aisément votre contenu quelque soit la charge. De quelques éléments à des milliards d'éléments par mois.
Confidentialité totale. Aucun besoin de modérateur humain. Le contenu de vos utilisateurs n'est vu par personne. La confidentialité est respectée.
Our tests show that humans struggle with AI video detection, while models specifically trained to detect AI videos vastly outperform human performance.
Êtes-vous prêt à relever le défi ? Faites notre test en ligne pour comparer vos résultats !

Nous offrons un ensemble complet de modèles pour analyser et modérer votre contenu visuel : Modération, Analyse ou Extraction de contenu.
Modérerez les images générées par vos utilisateurs. Détectez tout contenu indésirable tel que le contenu pour adulte, les propos haineux, la violence, la présence de mineurs et plus encore. En savoir plus sur notre API de Modération d'Images
JPEG PNG WebP GIF...
Analysez les vidéos statiques et les diffusions en direct en temps quasi réel. Repérez les contenus indésirables tels que la violence, les contenus pour adulte, les images illégales ou qui ne respectent pas vos conditions d'utilisation. En savoir plus sur notre API de Modération de Vidéos
MP4 AVI MOV HLS RTSP...
How can it be possible to find out if an image or video is AI-generated?
AI-generated media often contains subtle artifacts and inconsistencies that can be detected by specialized tools. These tools identify patterns reminiscent of synthetic images, helping distinguish them from real photos.
Can AI media detectors replace human judgment?
While the AI media detector provides real-time insights, it should never be used as a substitute for human judgment. Different detectors can have a varying levels of accuracy. It is essential to use your own discretion when reviewing their findings.
What are the limitations of AI media detectors?
AI media detectors can produce inaccurate results: false positives or false negatives. This detector may also struggle with content produced by AI media generators it has never encountered before, such as newly released ones. In some cases, images may also have been heavily edited in order to try to evade detection.
What does the provided score mean?
The score indicates the API's confidence in its prediction. A higher score suggests a greater likelihood that the content is AI-generated or AI-edited, while a lower score indicates the opposite. Even if the API returns a very high or very low score, such as 99% or 1%, it is important to consider the context and use human judgment in the final assessment.
How do you take into account new AI media generators?
We frequently test the API against new media generators as they enter the market, and take them into account to update the detectors to recognize them. Please note there usually is a brief window between the release of a new generator and its full integration into our system.
Results can be inaccurate. Rely on your own judgment and verify with additional context.