TwelveLabs | Developer hub

Products

Enterprise

Research

Developers

Company

Playground

Talk to Sales

Developer Hub

Explore our guides and examples to integrate TwelveLabs

Easily build features like semantic search, anomaly detection, content recommenders and capabilities tailored to you. Our API unlocks your video’s full potential.

Try our API.

Create index

Upload video

Generate (Video to Text)

Embeddings

Python

Node

import requests
url = "https://api.twelvelabs.io/v1.3/indexes"
headers = {
    "accept": "application/json",
    "Content-Type": "application/json"
}
response = requests.post(url, headers=headers)
print(response.text)

Follow these steps for a running start using TwelveLabs’ multimodal API.

Try our API.

Create index

Upload video

Generate (Video to Text)

Embeddings

Python

Node

import requests
url = "https://api.twelvelabs.io/v1.3/indexes"
headers = {
    "accept": "application/json",
    "Content-Type": "application/json"
}
response = requests.post(url, headers=headers)
print(response.text)

Follow these steps for a running start using TwelveLabs’ multimodal API.

Try our API.

Create index

Upload video

Generate (Video to Text)

Embeddings

Python

Node

import requests
url = "https://api.twelvelabs.io/v1.3/indexes"
headers = {
    "accept": "application/json",
    "Content-Type": "application/json"
}
response = requests.post(url, headers=headers)
print(response.text)

Follow these steps for a running start using TwelveLabs’ multimodal API.

Try our API.

Create index

Upload video

Generate (Video to Text)

Embeddings

Python

Node

import requests
url = "https://api.twelvelabs.io/v1.3/indexes"
headers = {
    "accept": "application/json",
    "Content-Type": "application/json"
}
response = requests.post(url, headers=headers)
print(response.text)

Follow these steps for a running start using TwelveLabs’ multimodal API.

Quick links

Jump right in with a
Sample App...

Discover what TwelveLabs can do by experimenting with our fully functional sample applications.

See all sample apps

Python

Who talked about us

Use semantic search capabilities of the platform to identify the most suitable influencers to reach out to.

Tutorial

Code

Node

Generate social media posts for your videos

Simplify the cross-platform video promotion workflow by generating unique posts for each social media platform.

Tutorial

Code

Python

Shade finder

This application uses the image-to-video search feature to find color shades in videos.

Tutorial

Code

Jump right in with a
Sample App...

Discover what TwelveLabs can do by experimenting with our fully functional sample applications.

See all sample apps

Python

Who talked about us

Use semantic search capabilities of the platform to identify the most suitable influencers to reach out to.

Tutorial

Code

Node

Generate social media posts for your videos

Simplify the cross-platform video promotion workflow by generating unique posts for each social media platform.

Tutorial

Code

Python

Shade finder

This application uses the image-to-video search feature to find color shades in videos.

Tutorial

Code

Integrations

Expand the functionality and efficiency of TwelveLabs’ Video Understanding Platform with our partner integrations.

Semantic video search plugin

The plugin allows you to accurately identify movements, actions, objects, people, sounds, on-screen text, and speech

The TwelveLabs handler

This guide outlines how you can use the handler and how the handler interfaces with the Twelve Labs Video Understanding Platform.

Semantic video search

This integration combines Twelve Labs' Embed API with MongoDB Atlas Vector Search to create an efficient semantic video search solution.

Integrations

Expand the functionality and efficiency of TwelveLabs’ Video Understanding Platform with our partner integrations.

Semantic video search plugin

The plugin allows you to accurately identify movements, actions, objects, people, sounds, on-screen text, and speech

The TwelveLabs handler

This guide outlines how you can use the handler and how the handler interfaces with the Twelve Labs Video Understanding Platform.

Semantic video search

This integration combines Twelve Labs' Embed API with MongoDB Atlas Vector Search to create an efficient semantic video search solution.

Browse by product

Explore documentation specific to each of our product offering.

Product overview

Find specific moments within your videos by describing the scene in natural language.

Generate

Generate text from videos - summary, chapters, highlights and more.

Embed

Build your own classifier using natural language and run instantly.

Browse by product

Explore documentation specific to each of our product offering.

Product overview

Find specific moments within your videos by describing the scene in natural language.

Generate

Generate text from videos - summary, chapters, highlights and more.

Embed

Build your own classifier using natural language and run instantly.

Our stable of models.

Learn more about TwelveLabs’ world-leading video foundation models.

Learn more

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.

Marengo

Our breakthrough video foundation model analyzes frames and their temporal relationships, along with speech and sound — a huge leap forward for search and any-to-any retrieval tasks.

Marengo

Our breakthrough video foundation model analyzes frames and their temporal relationships, along with speech and sound — a huge leap forward for search and any-to-any retrieval tasks.

Marengo

Our breakthrough video foundation model analyzes frames and their temporal relationships, along with speech and sound — a huge leap forward for search and any-to-any retrieval tasks.

Pegasus

Our powerful video-first language model integrates visual, audio, and speech information — and employs this deep video understanding to reach new heights in text generation.

Pegasus

Our powerful video-first language model integrates visual, audio, and speech information — and employs this deep video understanding to reach new heights in text generation.

Pegasus

Our powerful video-first language model integrates visual, audio, and speech information — and employs this deep video understanding to reach new heights in text generation.