TwelveLabs | Contact

🚀 Introducing Marengo 3: Our most advanced video foundation model yet. Built for enterprise scale and real-world complexity. Read more.

Products

Enterprise

Research

Developers

Company

Select Language

Playground

Talk to Sales

🚀 Introducing Marengo 3: Our most advanced video foundation model yet. Built for enterprise scale and real-world complexity. Read more.

Marengo 3.0 understands every moment in your video data

Search across scenes, objects, speech, actions, and motion
50% storage cost savings and 2x faster indexing
Advanced temporal and spatial reasoning for real video comprehension
Industry-first sports intelligence and entity-level recognition
Composed image plus text queries for precise retrieval

Try it free with your own videos in the Playground
Or book a demo to explore your use case

Try the Playground

Marengo 3.0 understands every moment in your video data

Search across scenes, objects, speech, actions, and motion
50% storage cost savings and 2x faster indexing
Advanced temporal and spatial reasoning for real video comprehension
Industry-first sports intelligence and entity-level recognition
Composed image plus text queries for precise retrieval

Try it free with your own videos in the Playground
Or book a demo to explore your use case

Try the Playground

Marengo 3.0 understands every moment in your video data

Search across scenes, objects, speech, actions, and motion
50% storage cost savings and 2x faster indexing
Advanced temporal and spatial reasoning for real video comprehension
Industry-first sports intelligence and entity-level recognition
Composed image plus text queries for precise retrieval

Try it free with your own videos in the Playground
Or book a demo to explore your use case

Try the Playground

TRUSTED BY

Marengo transforms text, audio, image, and video into numerical representations called embeddings.

Embeddings enable unsurpassed information retrieval. Now, you can perform powerful cross-modal searches – across text, audio, image and video.

This any-to-any retrieval can transform applications. Content discovery, recommendation systems, description and analysis will all change for good.

At TwelveLabs, we’re developing video-native AI systems that can solve problems with human-level reasoning. Helping machines learn about the world — and enabling humans to retrieve, capture, and tell their visual stories better.

Our Research

Marengo

3.0

Powered Features

Where power meets potential.

Introducing ‘any-to-any’ search

Marengo’s state-of-the-art ‘any-to-any’ search helps you pinpoint exact moments in vast video libraries, or allow customers to find any video moment within your platform.