Twelve Labs Video Understanding API is an AI-powered video understanding solution that extracts information such as movements, objects, sounds, text on screen, and speech from your videos and allows you to find specific moments using everyday language.

Why use Twelve Labs Video Understanding API?

The following sections describe the key capabilities of Twelve Labs Video Understanding API and compare it to other solutions.

Key capabilities

Developers using Twelve Labs Video Understanding API have access to the following key capabilities:

• Relevance: Find the exact moment you need within your video library using full text-based search queries.
• Intuitive: Integrate more than twenty state-of-the-art deep learning models into your applications in three simple steps.
• Speed: Receive your search results within seconds.
• Scalability: With Twelve Labs, your applications rely on a cloud-native distributed infrastructure that can handle thousands of simultaneous indexing and search requests.

📘

Note

Twelve Labs is continuously adding new features. See the Roadmap page for details.

Twelve Labs Video Understanding API compared to other solutions

The table below provides a basic comparison between Twelve Labs Video Understanding API and other cloud-based solutions:

• Use a single API to access the Twelve Labs AI-powered video understanding service that allows you to find the information you’re looking for in your videos. Focus on building your application instead of collating data from separate image and speech APIs.
• Write complex semantic queries in everyday language that semantically describe the exact moment you want to find in your videos instead of filtering on pre-generated tags.
• Adapt the AI model to your domain instead of relying on a single model. Note that this feature is on the roadmap.