AI for Security Video Analysis

Platform

Pricing

Solutions

Build

Resources

Company

Select Language

Playground

Talk to Sales

VIDEO AI FOR SECURITY

Understand behavior, not just motion.

Multimodal AI that reasons across cameras, sources, and time. Search footage in natural language, reconstruct incidents across feeds, and surface anomalies before they become threats.

Talk to Sales

Multimodal AI that reasons across cameras, sources, and time. Search footage in natural language, reconstruct incidents across feeds, and surface anomalies before they become threats.

Talk to Sales

TRUSTED BY

Built for your workflow.

How teams use TwelveLabs to get more from their video.

Behavioral Surveillance

Detect patterns and track activity across live and recorded feeds with semantic understanding of what is actually happening, not just where pixels moved. The model reasons about visual, audio, and contextual signals together, catching events that motion-only systems miss entirely.

Evidence Search & Reconstruction

Trace a person, vehicle, or event across every camera that captured it. Build a complete timeline from fragments in minutes instead of days. Output integrates with your existing VMS and case management tools.

Anomaly & Pattern Detection

Surface behavioral deviations from baseline across months of archived footage. Recurring patterns, unusual access, and emerging trends become visible before they become incidents, with confidence scores your team can tune to the right threshold for your environment.

Built for your workflow.

How teams use TwelveLabs to get more from their video.

Behavioral Surveillance

Evidence Search & Reconstruction

Anomaly & Pattern Detection

Built for security at scale, deployed where your data lives

Index every camera feed once. Query forever. New model upgrades apply retroactively to your archive, so the system gets sharper over time without re-ingestion.

+13.1%

Pegasus 1.5 over Gemini 3.1 Pro on Multimodal Prompting

10x

Faster content review and compliance scanning.

4 hrs

Single video, one API call

Python

Node.js

import requests
 
# Step 2: Define the API URL and the specific endpoint
API_URL = "https://api.twelvelabs.io/v1.3"
INDEXES_URL = f"{API_URL}/indexes"
 
# Step 3: Create the necessary headers for authentication
headers = {
    "x-api-key": "<YOUR_API_KEY>"
}
 
# Step 4: Prepare the data payload for your API request
INDEX_NAME = "<YOUR_INDEX_NAME>"
data = {
    "models": [
        {
            "model_name": "marengo3.0",
            "model_options": ["visual", "audio"]
        }
    ]
}

Integrate with your personalized SDK — and your vision.

Do more with your video from day one with our easy APIs and developer-friendly SDKs. This is AI made to work for you, ready to integrate and adapt.

Get SDK

Integrate with your personalized SDK — and your vision.

Do more with your video from day one with our easy APIs and developer-friendly SDKs. This is AI made to work for you, ready to integrate and adapt.

Get SDK

See All

Sample apps

See All

Node

Security Analysis

Process security footage, dash camera videos, and CCTV recordings to identify key security events.

Try this example

Node

Workplace Safety

Building A Workplace Safety Compliance Application with TwelveLabs and NVIDIA VSS

Try this example

Python

Recursive Video Enhancement

Building Recurser: Iterative AI Video Enhancement with TwelveLabs and Google Veo

Try this example

Customer Stories

“It's essential for our business to access exact moments in games to package the best content to our fans. Multimodal AI is a game-changer in surfacing the best content you have available.”
Brad Boim Senior Director, Media Management & Post Production, NFL Media
“With generative AI, we can mine neglected aspects of videos, both in and out of game, to create content tailored to each fan while maintaining the brand identity of each team preserved in team-specific generative models. This revolutionary approach allows creative teams to focus on high-level strategy while providing an unprecedented scale of personalized, engaging content”
-Farah Bastien
“TwelveLabs is one-of-a kind. For us to serve as a design partner to be the first city in the world to deploy this kind of advanced technology using foundational models is a true opportunity we appreciate.”
CTO, Sejong City
“TwelveLabs has developed a powerful and user-friendly technology that allows users to ask questions about videos and receive answers as if by magic!”
Jorge Torres Co-Founder and CEO, MindsDB
“Building with TwelveLabs was an easy and powerful way to enhance our video datasets. Integration with FiftyOne was made simple with their excellent documentation and tutorials.”
Daniel Gural Machine Learning Evangelist, Voxel51
There is nothing in the world like TwelveLabs. It’s easy to integrate, finds what’s valuable, and the accuracy is astounding. Our video data opens new doors to business areas we’d only imagined.”
Pedro Almeida CEO, Mindprober
“The TwelveLabs API continually amazes me in searching ALL parts of a video. With each search, I discover new results and possibilities of the technology for our customers.”
Michael Philips Chief Product Officer, Source Digital

Customer Stories

“It's essential for our business to access exact moments in games to package the best content to our fans. Multimodal AI is a game-changer in surfacing the best content you have available.”
Brad Boim Senior Director, Media Management & Post Production, NFL Media
“With generative AI, we can mine neglected aspects of videos, both in and out of game, to create content tailored to each fan while maintaining the brand identity of each team preserved in team-specific generative models. This revolutionary approach allows creative teams to focus on high-level strategy while providing an unprecedented scale of personalized, engaging content”
-Farah Bastien
“TwelveLabs is one-of-a kind. For us to serve as a design partner to be the first city in the world to deploy this kind of advanced technology using foundational models is a true opportunity we appreciate.”
CTO, Sejong City
“TwelveLabs has developed a powerful and user-friendly technology that allows users to ask questions about videos and receive answers as if by magic!”
Jorge Torres Co-Founder and CEO, MindsDB
“Building with TwelveLabs was an easy and powerful way to enhance our video datasets. Integration with FiftyOne was made simple with their excellent documentation and tutorials.”
Daniel Gural Machine Learning Evangelist, Voxel51
There is nothing in the world like TwelveLabs. It’s easy to integrate, finds what’s valuable, and the accuracy is astounding. Our video data opens new doors to business areas we’d only imagined.”
Pedro Almeida CEO, Mindprober
“The TwelveLabs API continually amazes me in searching ALL parts of a video. With each search, I discover new results and possibilities of the technology for our customers.”
Michael Philips Chief Product Officer, Source Digital

Customer Stories

“It's essential for our business to access exact moments in games to package the best content to our fans. Multimodal AI is a game-changer in surfacing the best content you have available.”
Brad Boim Senior Director, Media Management & Post Production, NFL Media
“With generative AI, we can mine neglected aspects of videos, both in and out of game, to create content tailored to each fan while maintaining the brand identity of each team preserved in team-specific generative models. This revolutionary approach allows creative teams to focus on high-level strategy while providing an unprecedented scale of personalized, engaging content”
-Farah Bastien
“TwelveLabs is one-of-a kind. For us to serve as a design partner to be the first city in the world to deploy this kind of advanced technology using foundational models is a true opportunity we appreciate.”
CTO, Sejong City
“TwelveLabs has developed a powerful and user-friendly technology that allows users to ask questions about videos and receive answers as if by magic!”
Jorge Torres Co-Founder and CEO, MindsDB
“Building with TwelveLabs was an easy and powerful way to enhance our video datasets. Integration with FiftyOne was made simple with their excellent documentation and tutorials.”
Daniel Gural Machine Learning Evangelist, Voxel51
There is nothing in the world like TwelveLabs. It’s easy to integrate, finds what’s valuable, and the accuracy is astounding. Our video data opens new doors to business areas we’d only imagined.”
Pedro Almeida CEO, Mindprober
“The TwelveLabs API continually amazes me in searching ALL parts of a video. With each search, I discover new results and possibilities of the technology for our customers.”
Michael Philips Chief Product Officer, Source Digital