For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Sample appsIntegrationsDiscordPlaygroundDevEx repo
GuidesSDK ReferenceAPI Reference
GuidesSDK ReferenceAPI Reference
  • TwelveLabs API
    • Introduction
    • Authentication
  • API Reference
    • Manage indexes
    • Upload content
    • Index content
    • Manage videos
    • Manage entities
    • Any-to-video search
    • Create embeddings v2
    • Create embeddings v1
      • Create video embeddings
        • The video embedding object
        • POSTCreate a video embedding task
        • GETList video embedding tasks
        • GETRetrieve the status of a video embedding task
        • GETRetrieve video embeddings
      • Create text, image, and audio embeddings
    • Analyze and segment videos
    • Error codes
LogoLogo
Sample appsIntegrationsDiscordPlaygroundDevEx repo
API ReferenceCreate embeddings v1Create video embeddings

Retrieve video embeddings

GET
https://api.twelvelabs.io/v1.3/embed/tasks/:task_id
GET
/v1.3/embed/tasks/:task_id
$curl https://api.twelvelabs.io/v1.3/embed/tasks/663da73b31cdd0c1f638a8e6 \
>     -H "x-api-key: <apiKey>"
1{
2  "_id": "663e16ac4d11aff765088b3a",
3  "created_at": "2024-03-01T00:00:00Z",
4  "model_name": "marengo3.0",
5  "status": "ready",
6  "video_embedding": {
7    "metadata": {
8      "duration": 18,
9      "input_filename": "01.mp4",
10      "video_clip_length": 6,
11      "video_embedding_scope": [
12        "clip",
13        "video"
14      ]
15    },
16    "segments": [
17      {
18        "embedding_option": "visual",
19        "embedding_scope": "clip",
20        "end_offset_sec": 6,
21        "float": [
22          -0.060086973,
23          0.016479108
24        ],
25        "start_offset_sec": 0
26      },
27      {
28        "embedding_option": "visual",
29        "embedding_scope": "clip",
30        "end_offset_sec": 12,
31        "float": [
32          -0.056660935,
33          0.012404642
34        ],
35        "start_offset_sec": 6
36      },
37      {
38        "embedding_option": "visual",
39        "embedding_scope": "video",
40        "end_offset_sec": 12,
41        "float": [
42          -0.05971131,
43          -0.00859428
44        ],
45        "start_offset_sec": 0
46      },
47      {
48        "embedding_option": "audio",
49        "embedding_scope": "clip",
50        "end_offset_sec": 6,
51        "float": [
52          -0.060086973,
53          0.016479108
54        ],
55        "start_offset_sec": 0
56      },
57      {
58        "embedding_option": "audio",
59        "embedding_scope": "clip",
60        "end_offset_sec": 12,
61        "float": [
62          -0.056660935,
63          0.012404642
64        ],
65        "start_offset_sec": 6
66      },
67      {
68        "embedding_option": "audio",
69        "embedding_scope": "clip",
70        "end_offset_sec": 18,
71        "float": [
72          -0.05971131,
73          -0.00859428
74        ],
75        "start_offset_sec": 12
76      },
77      {
78        "embedding_option": "audio",
79        "embedding_scope": "video",
80        "end_offset_sec": 12,
81        "float": [
82          -0.05971131,
83          -0.00859428
84        ],
85        "start_offset_sec": 0
86      }
87    ]
88  }
89}

This method retrieves embeddings for a specific video embedding task. Ensure the task status is ready before invoking this method. Refer to the Retrieve the status of a video embedding tasks page for instructions on checking the task status.

Was this page helpful?
Previous

Create text, image, and audio embeddings

Next
Built with

Authentication

x-api-keystring

Your API key.

Note

You can find your API key on the API Keys page.

Path parameters

task_idstringRequired
The unique identifier of your video embedding task.

Query parameters

embedding_optionlist of enumsOptional
Specifies which types of embeddings to retrieve. Values: `visual`, `audio`, `transcription`. For details, see the [Embedding options](/v1.3/docs/concepts/modalities#embedding-options) section. <Note title="Note"> The platform returns all available embeddings when you omit this parameter. </Note>
Allowed values:

Response

Video embeddings have successfully been retrieved.
_idstring
The unique identifier of the video embedding task.
created_atstringformat: "date-time"

A string representing the date and time, in RFC 3339 format (“YYYY-MM-DDTHH:mm:ssZ”), when the resource was created.

model_namestring
The name of the video understanding model the platform used to create the embedding.
statusstring

A string indicating the status of the video indexing task. It can take one of the following values: processing, ready or failed.

updated_atstringformat: "date-time"

A string representing the date and time, in RFC 3339 format (“YYYY-MM-DDTHH:mm:ssZ”), when the resource was last updated.

video_embeddingobject

Errors

400
Bad Request Error

Specifies which types of embeddings to retrieve. Values: visual, audio, transcription. For details, see the Embedding options section.

Note

The platform returns all available embeddings when you omit this parameter.