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>"

{
  "_id": "663e16ac4d11aff765088b3a",
  "model_name": "marengo3.0",
  "status": "ready",
  "created_at": "2024-03-01T00:00:00Z",
  "video_embedding": {
    "metadata": {
      "input_filename": "01.mp4",
      "video_clip_length": 6,
      "video_embedding_scope": [
        "clip",
        "video"
      ],
      "duration": 18
    },
    "segments": [
      {
        "float": [
          -0.060086973,
          0.016479108
        ],
        "start_offset_sec": 0,
        "end_offset_sec": 6,
        "embedding_option": "visual",
        "embedding_scope": "clip"
      },
      {
        "float": [
          -0.056660935,
          0.012404642
        ],
        "start_offset_sec": 6,
        "end_offset_sec": 12,
        "embedding_option": "visual",
        "embedding_scope": "clip"
      },
      {
        "float": [
          -0.05971131,
          -0.00859428
        ],
        "start_offset_sec": 0,
        "end_offset_sec": 12,
        "embedding_option": "visual",
        "embedding_scope": "video"
      },
      {
        "float": [
          -0.060086973,
          0.016479108
        ],
        "start_offset_sec": 0,
        "end_offset_sec": 6,
        "embedding_option": "audio",
        "embedding_scope": "clip"
      },
      {
        "float": [
          -0.056660935,
          0.012404642
        ],
        "start_offset_sec": 6,
        "end_offset_sec": 12,
        "embedding_option": "audio",
        "embedding_scope": "clip"
      },
      {
        "float": [
          -0.05971131,
          -0.00859428
        ],
        "start_offset_sec": 12,
        "end_offset_sec": 18,
        "embedding_option": "audio",
        "embedding_scope": "clip"
      },
      {
        "float": [
          -0.05971131,
          -0.00859428
        ],
        "start_offset_sec": 0,
        "end_offset_sec": 12,
        "embedding_option": "audio",
        "embedding_scope": "video"
      }
    ]
  }
}

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.

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 section.

Note

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

Allowed values:

Response

Video embeddings have successfully been retrieved.

_idstringOptional

The unique identifier of the video embedding task.

model_namestringOptional

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

statusstringOptional

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

created_atstringOptionalformat: "date-time"

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

updated_atstringOptionalformat: "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_embeddingobjectOptional

An object containing the metadata associated with the embedding.

Errors

400

Bad Request Error