The TwelveLabs Video Understanding Platform analyzes videos by integrating images, audio, speech, and text, offering a deeper understanding than single-modal methods. It captures complex relationships between these elements, detects subtle details, and supports natural language queries and images for intuitive and precise use.

Key features:

Improved accuracy: Multimodal integration enhances accuracy.
Easy interaction: Natural language queries simplify searches.
Advanced search: Enables image-based queries for precise results.
Fewer errors: Multi-faceted analysis reduces misinterpretation.
Time savings: Quickly finds relevant clips without manual review.

Use cases:

Spoken word search: Find video segments where specific words or phrases are spoken.
Visual element search: Locate video segments that match descriptions of visual elements or scenes.
Action or event search: Identify video segments that depict specific actions or events.
Image similarity search: Find video segments that visually resemble a provided image.

To understand how your usage is measured and billed, see the Pricing page.

Note

You can only perform searches at the individual index level, meaning you can only search within one index per request and cannot search at the video level or across multiple indexes simultaneously.

Prerequisites

To use the platform, you need an API key:

1
If you don’t have an account, sign up for a free account.
2
Go to the API Key page.
3
Select the Copy icon next to your key.

Ensure the pre-release version of the TwelveLabs SDK is installed on your computer:

$ pip install twelvelabs --pre

The videos you wish to use must meet the following requirements:
- Video resolution: Must be at least 360x360 and must not exceed 3840x2160.
- Aspect ratio: Must be one of 1:1, 4:3, 4:5, 5:4, 16:9, 9:16, or 17:9.
- Video and audio formats: Your video files must be encoded in the video and audio formats listed on the FFmpeg Formats Documentation page. For videos in other formats, contact us at support@twelvelabs.io.
- Duration: Must be between 4 seconds and 2 hours (7,200s).
- File size: Must not exceed 2 GB.
  If you require different options, contact us at support@twelvelabs.io.
If you wish to use images as queries, ensure that your images meet the following requirements:
- Format: JPEG and PNG.
- Dimension: Must be at least 64 x 64 pixels.
- Size: Must not exceed 5MB.

Complete example

This complete example shows how to create an index, upload a video, and perform search requests using text and image queries. Ensure you replace the placeholders surrounded by <> with your values.

1 from twelvelabs import TwelveLabs
2 from twelvelabs.indexes import IndexesCreateRequestModelsItem
3 from twelvelabs.tasks import TasksRetrieveResponse
4 
5 # 1. Initialize the client
6 client = TwelveLabs(api_key="<YOUR_API_KEY>")
7 
8 # 2. Create an index
9 index = client.indexes.create(
10     index_name="<YOUR_INDEX_NAME>",
11     models=[
12         IndexesCreateRequestModelsItem(
13             model_name="marengo2.7",
14             model_options=["visual", "audio"]
15         )
16     ]
17 )
18 print(f"Created index: id={index.id}")
19 
20 # 3. Upload a video
21 task = client.tasks.create(
22     index_id=index.id, video_url="<YOUR_VIDEO_URL>")
23 print(f"Created task: id={task.id}")
24 
25 # 4. Monitor the indexing process
26 def on_task_update(task: TasksRetrieveResponse):
27     print(f"  Status={task.status}")
28 
29 task = client.tasks.wait_for_done(sleep_interval= 5, task_id=task.id, callback=on_task_update)
30 if task.status != "ready":
31     raise RuntimeError(f"Indexing failed with status {task.status}")
32 print(
33     f"Upload complete. The unique identifier of your video is {task.video_id}.")
34 
35 # 5. Perform a search request
36 search_pager = client.search.query(
37     index_id=index.id,
38     query_text="<YOUR_QUERY>",
39     search_options=["visual", "audio"],
40     # operator="or"
41 )
42 
43 # 6. Process the search results
44 print("Search results:")
45 for clip in search_pager:
46     print(
47         f" video_id {clip.video_id} score={clip.score} start={clip.start} end={clip.end} confidence={clip.confidence}"
48     )

Step-by-step guide

Python

Node.js

Import the SDK and initialize the client

Create a client instance to interact with the TwelveLabs Video Understanding Platform.
Function call: You call the constructor of the TwelveLabs class.
Parameters:

api_key: The API key to authenticate your requests to the platform.

Return value: An object of type TwelveLabs configured for making API calls.

Specify the index containing your videos

Indexes help you organize and search through related videos efficiently. This example creates a new index, but you can also use an existing index by specifying its unique identifier. See the Indexes page for more details on creating an index.
Function call: You call the indexes.create function.
Parameters:

index_name: The name of the index.
models: An array specifying your model configuration. This example enables the Marengo video understanding model and the visual and audio model options.

Return value: An object containing, among other information, a field named id representing the unique identifier of the newly created index.

Upload videos

To perform any downstream tasks, you must first upload your videos, and the platform must finish indexing them.
Function call: You call the tasks.create function.
Parameters:

index_id: The unique identifier of your index.
video_url or video_file: The publicly accessible URL or the path of your video file.

Return value: An object of type TasksCreateResponse that you can use to track the status of your video upload and indexing process. This object contains, among other information, the following fields:

id: The unique identifier of your video indexing task.
video_id: The unique identifier of your video.

Note

You can also upload multiple videos in a single API call. For details, see the Cloud-to-cloud integrations page.

Monitor the indexing process

The platform requires some time to index videos. Check the status of the video indexing task until it’s completed.
Function call: You call the tasks.wait_for_done function.
Parameters:

sleep_interval: The time interval, in seconds, between successive status checks. In this example, the method checks the status every five seconds.
task_id: The unique identifier of your video indexing task.
callback: A callback function that the SDK executes each time it checks the status.

Return value: An object of type TasksRetrieveResponse containing, among other information, a field named status representing the status of your task. Wait until the value of this field is ready.

Perform a search request

Perform a search within your index using a text or image query.

Text queries

Image queries

Function call: You call the search.query method.
Parameters:

index_id: The unique identifier of the index.
query_text: Your search query. Note that the platform supports full natural language-based search.
search_options: The modalities the platform uses when performing a search. This example searches using visual and audio cues.
(Optional) operator: The logical operator, either or or and, specifies how your search combines multiple sources of information; it defaults to or. Use this parameter when the search_options parameter lists more than one source of information. For example, when you set this parameter to and, the search returns video segments matching all specified sources of information.

Return value: An object of type SyncPager[SearchItem] that can be iterated to access search results. Each item contains the following fields, among other information:

video_id: The unique identifier of the video that matched your search terms.
start: The start time of the matching video clip, expressed in seconds.
end: The end time of the matching video clip, expressed in seconds.
score: A quantitative value determined by the platform representing the level of confidence that the results match your search terms.
confidence: A quantitative value determined by the platform representing the level of confidence that the results match your search terms.

Process the search results

This example iterates over the results using a for loop to display the search results to the standard output.