高度な検索機能。

見逃しなし。

すべてを理解。

必要な瞬間を正確に特定する、超高速かつ文脈理解型の検索結果を提供します。タグに依存しない、マルチモーダル理解の新次元へと導きます。

Playgroundをお試しください

Products

Enterprise

Research

Developers

Company

日本語

Select Language

Playground

Talk to Sales

Search 01

テキストや画像で検索

自然言語によるクエリや画像を用いて、ペタバイト級の膨大なデータの中から、意味的に関連する瞬間を迅速に特定することが可能です。

Search 01

Search by text or image

Use natural language queries or images to quickly uncover semantically-related moments, even across petabytes of data.

Search 02

モダリティを横断して検索

サウンド、発話、テキスト、映像まで、動画内のあらゆる情報にアクセスでき、これまで見えなかった洞察を引き出します。

Search 02

Search across modalities

Sound, speech, text and visuals — make all the information in your video reachable, and find insights previously hidden.

Search 03

ドメイン言語で検索

TwelveLabsの基盤モデルをお客様のビジネス特有のニュアンスに合わせてファインチューニングでき、チームが日常的に使う自然な言語で検索できる環境を実現します。

Search 03

Search in your domain language

Fine-tune our foundation models to the nuances of your business, and let your team search in language that   comes naturally.

Search is just the beginning.

Scene Selection

Identify the most impactful scenes to power production workflows.

Content Discovery

Search for specific moments within footage or across vast video archives.

Customer Search

Let customers easily find any video moment within your platform.

Asset Management

Comb through petabytes of data using natural  language queries.

Surveillance

Pinpoint precise moments to conduct investigations and manage evidence.

Multilingual Search

Let users search in their language, with over 100 languages supported.

Contextual Advertising

Find and match ads to relevant media moments for increased engagement.

Domain-Specific Search

Fine-tune our models so your   team can search in the language   of their sector.

Search is just the beginning.

Scene Selection

Identify the most impactful scenes to power production workflows.

Content Discovery

Search for specific moments within footage or across vast video archives.

Customer Search

Let customers easily find any video moment within your platform.

Asset Management

Comb through petabytes of data using natural  language queries.

Surveillance

Pinpoint precise moments to conduct investigations and manage evidence.

Multilingual Search

Let users search in their language, with over 100 languages supported.

Contextual Advertising

Find and match ads to relevant media moments for increased engagement.

Domain-Specific Search

Fine-tune our models so your   team can search in the language   of their sector.

Search is just the beginning.

Scene Selection

Identify the most impactful scenes to power production workflows.

Content Discovery

Search for specific moments within footage or across vast video archives.

Customer Search

Let customers easily find any video moment within your platform.

Asset Management

Comb through petabytes of data using natural  language queries.

Surveillance

Pinpoint precise moments to conduct investigations and manage evidence.

Multilingual Search

Let users search in their language, with over 100 languages supported.

Contextual Advertising

Find and match ads to relevant media moments for increased engagement.

Domain-Specific Search

Fine-tune our models so your   team can search in the language   of their sector.

Sample Apps

Python

Olympic Video Classification Application

The Olympics Video Clips Classification Application is a powerful tool designed to categorize various Olympic sports using video clips.

Try this sample app

Node

Shade Finder App: Pinpoint Specific Colors in Videos

Whether you're looking to find the perfect berry-toned lipstick or just curious about spotting specific colors in your videos, this guide will help you leverage cutting-edge AI to do so effortlessly.

Try this sample app

PYTHON

Video Highlight Generator

The YouTube Chapter Highlight Generator is a tool developed to automatically generate chapter timestamps for YouTube videos.

Try this sample app

Python

Node

from twelvelabs import TwelveLabs
import os

client = TwelveLabs("<YOUR_API_KEY>")

# Create new Index
index = client.index.create(        
     name="My First Index",
     engines=[
       {                
         "name": "marengo2.7",
         "options": ["visual", "audio"],
       },
     ],
  )
# Create new Task on Index (Upload the video)
video_path = os.path.join(os.path.dirname(__file__), "<YOUR_FILE_PATH>")
task = client.task.create(index_id=index.id, file=video_path,
language="en")

# Wait for indexing to finish
task.wait_for_done()

# Search from your index
query = "An artist climbing up the ladder that he painted."
result = client.search.query(index.id, query, ["visual", "audio"])
‍print(result)

Python

Node

from twelvelabs import TwelveLabs
import os

client = TwelveLabs("<YOUR_API_KEY>")

# Create new Index
index = client.index.create(        
     name="My First Index",
     engines=[
       {                
         "name": "marengo2.7",
         "options": ["visual", "audio"],
       },
     ],
  )
# Create new Task on Index (Upload the video)
video_path = os.path.join(os.path.dirname(__file__), "<YOUR_FILE_PATH>")
task = client.task.create(index_id=index.id, file=video_path,
language="en")

# Wait for indexing to finish
task.wait_for_done()

# Search from your index
query = "An artist climbing up the ladder that he painted."
result = client.search.query(index.id, query, ["visual", "audio"])
‍print(result)

Python

Node

from twelvelabs import TwelveLabs
import os

client = TwelveLabs("<YOUR_API_KEY>")

# Create new Index
index = client.index.create(        
     name="My First Index",
     engines=[
       {                
         "name": "marengo2.7",
         "options": ["visual", "audio"],
       },
     ],
  )
# Create new Task on Index (Upload the video)
video_path = os.path.join(os.path.dirname(__file__), "<YOUR_FILE_PATH>")
task = client.task.create(index_id=index.id, file=video_path,
language="en")

# Wait for indexing to finish
task.wait_for_done()

# Search from your index
query = "An artist climbing up the ladder that he painted."
result = client.search.query(index.id, query, ["visual", "audio"])
‍print(result)