Initializing…

Marengo 3.0

Our most advanced video foundation  model yet. Built for enterprise scale

Video unlocked as data.

Search it, analyze it, put it to work. Instantly and at scale.

Try Playground

Talk to Sales

Built for the most demanding video workflows

Designed for organizations working with video at scale – turning raw, passive footage into a strategic asset teams can actually use.

Search & Discover

Search entire video libraries using natural language. Locate specific actions, scenes, dialogue, and even human emotions across hours or years of footage – no tags needed.

Segment Content

Ensure Compliance

Create Highlights

Generate Insights

Built for the most demanding video workflows

Designed for organizations working with video at scale – turning raw, passive footage into a strategic asset teams can actually use.

Search & Discover

Search entire video libraries using natural language. Locate specific actions, scenes, dialogue, and even human emotions across hours or years of footage – no tags needed.

Segment Content

Automatically identify natural breaks, scene changes, and pacing shifts in long-form video – so ads land where viewers expect them, not where they interrupt.

Ensure Compliance

Identify policy risks, sensitive content, and brand safety issues at scale with explainable AI — so teams can review faster, with confidence in every decision.

Create Highlights

Quickly identify standout scenes or plays across hours of footage to create highlights and reels – without manual scrubbing.

Generate Insights

Analyze video at scale to surface patterns and signals – so teams can quickly see what’s working and make better decisions.

Built for the most demanding video workflows

Designed for organizations working with video at scale – turning raw, passive footage into a strategic asset teams can actually use.

Search & Discover

Search entire video libraries using natural language. Locate specific actions, scenes, dialogue, and even human emotions across hours or years of footage – no tags needed.

Segment Content

Automatically identify natural breaks, scene changes, and pacing shifts in long-form video – so ads land where viewers expect them, not where they interrupt.

Ensure Compliance

Identify policy risks, sensitive content, and brand safety issues at scale with explainable AI — so teams can review faster, with confidence in every decision.

Create Highlights

Quickly identify standout scenes or plays across hours of footage to create highlights and reels – without manual scrubbing.

Generate Insights

Analyze video at scale to surface patterns and signals – so teams can quickly see what’s working and make better decisions.

One

API.

Endless applications.

Build custom video intelligence tools for teams in sports, advertising, security, media, and government.

Creative Industries

AdTech and Marketing

Public Sector

Public Sector

Evidence management, anomaly detection, after incident reporting, all done in minutes using TwelveLabs video intelligence.

Learn more

Creative Industries

Turn archives from liabilities to strategic assets. Within seconds: timestamped clips, from every year, every shoot. What used to take a research team three days takes three seconds.

Learn more

AdTech and Marketing

Actually contextual targeting, driven by understanding, not metadata. Place ads only in brand-safe scenes, no tags, no manual review.

Learn more

Public Sector

Evidence management, anomaly detection, after incident reporting, all done in minutes using TwelveLabs video intelligence.

Learn more

Creative Industries

Turn archives from liabilities to strategic assets. Within seconds: timestamped clips, from every year, every shoot. What used to take a research team three days takes three seconds.

Learn more

AdTech and Marketing

Actually contextual targeting, driven by understanding, not metadata. Place ads only in brand-safe scenes, no tags, no manual review.

Learn more

Creative Industries

AdTech and Marketing

Public Sector

Public Sector

Evidence management, anomaly detection, after incident reporting, all done in minutes using TwelveLabs video intelligence.

Learn more

Creative Industries

Turn archives from liabilities to strategic assets. Within seconds: timestamped clips, from every year, every shoot. What used to take a research team three days takes three seconds.

Learn more

AdTech and Marketing

Actually contextual targeting, driven by understanding, not metadata. Place ads only in brand-safe scenes, no tags, no manual review.

Learn more

Create, scale & move faster with video

Designed for organizations working with video at scale – turning raw, passive footage into a strategic asset teams can actually use.

98%

Less time spent generating highlights.

7x

More clips produced per editor, per day.

10x

Faster content review and compliance scanning.

80%+

Less time spent searching, segmenting and manually reviewing.

Secure by design

TwelveLabs is built to meet enterprise security and compliance requirements from day one. With SOC 2 Type II certification, encrypted data handling, and deployment options across cloud, private cloud, or on-prem, teams can work with sensitive video data – without compromising control, privacy, or reliability.

Learn more

Secure by design

Learn more

The models behind the TwelveLabs platform

Twelve Labs is built on a set of purpose-built models, each optimised for a different layer of video understanding – from search and embedding, to deep analysis at scale.

Learn more

Twelve Labs is built on a set of purpose-built models, each optimised for a different layer of video understanding – from search and embedding, to deep analysis at scale.

Learn more

Marengo is our multimodal encoder that understands video across vision, audio, and language. It powers natural-language search and embedding, enabling teams to integrate video understanding directly into their products via APIs.

Pegasus translates text into video understanding at scale. It powers analysis workflows like segmentation, metadata generation, and structured outputs that support automation, insight, and downstream decision-making.

How video intelligence works

Infrastructure for video intelligence – turning raw video into searchable, AI-ready data at massive scale.

Developer Hub

1. Infrastructure

TwelveLabs integrates with the tools and systems teams already use, making it easy to bolt on video intelligence without reworking your stack or processes.

Learn more

API's

SDK's

Integrations

How video intelligence works

Infrastructure for video intelligence – turning raw video into searchable, AI-ready data at massive scale.

Developer Hub

1. Infrastructure

TwelveLabs integrates with the tools and systems teams already use, making it easy to bolt on video intelligence without reworking your stack or processes.

Learn more

API's

SDK's

Integrations

How video intelligence works

Infrastructure for video intelligence – turning raw video into searchable, AI-ready data at massive scale.

Developer Hub

1. Infrastructure

TwelveLabs integrates with the tools and systems teams already use, making it easy to bolt on video intelligence without reworking your stack or processes.

Learn more