The TwelveLabs Video Understanding Platform identifies objects, actions, speech, and text in your video content. Access the following core capabilities through simple APIs:

Search: Find specific moments in your videos using text or image queries. Search across visual content, spoken words, on-screen text, and audio.
Analyze: Generate summaries, chapters, highlights, titles, and answers to questions about your video content.
Embed: Create multimodal embeddings for semantic search, recommendations, classification, and other downstream AI tasks.

Most popular

Quickstart guides

Get started quickly with simplified examples and core parameters.

Guides

Comprehensive guides covering more features and parameters.

API Reference

Complete documentation for each endpoint.

TwelveLabs SDKs

Discover how to utilize the official client libraries to streamline your integration process.

Playground

Test the capabilities of the platform before writing any code.

TwelveLabs models

Marengo

Embedding model, proficient at performing cross-modal searches - across text, audio, image, and video. Use this model for search and embedding tasks.

Pegasus

Generative model that can answer questions, generate creative outputs, and provide detailed analysis of any video. Use this model to analyze videos and generate text based on their content.