Get AI task result

curl --request GET \
  --url https://api.gcore.com/streaming/ai/tasks/{task_id} \
  --header 'Authorization: <api-key>'

{
  "task_id": "aafe70c6-0000-0000-0000-327b65f7670f",
  "task_data": {
    "url": "https://demo-public.gvideo.io/videos/2675_TVKIqpTO7tEFoFg/qid5774v1_h264_450_360.mp4",
    "category": "sport",
    "client_id": 2675,
    "task_name": "content-moderation"
  },
  "progress": 100,
  "status": "SUCCESS",
  "processing_time": {
    "started_at": "2024-07-13T12:30:00.000Z",
    "completed_at": "2024-07-13T12:31:02.900Z",
    "total_time_sec": 62.901
  },
  "result": {
    "sport_detected": true,
    "detection_results": [
      "shooting goal (soccer)",
      "playing cricket"
    ],
    "frames": [
      {
        "label": "shooting goal (soccer)",
        "frame_number": 68,
        "confidence": 1
      },
      {
        "label": "playing cricket",
        "frame_number": 728,
        "confidence": 0.99
      }
    ]
  }
}

Get AI task result

This is the single method to check the execution status of an AI task, and obtain the result of any type of AI task.

Based on the results of processing, the “result” field will contain an answer corresponding to the type of the initially created task:

ASR: Transcribe video
ASR: Translate subtitles
CM: Sports detection
CM: Not Safe For Work (NSFW) content detection
CM: Soft nudity detection
CM: Hard nudity detection
CM: Objects recognition (soon)
etc… (see other methods from /ai/ domain)

A queue is used to process videos. The waiting time depends on the total number of requests in the system, so sometimes you will have to wait.

Statuses:

RECEIVED – the task is accepted by the system
PENDING – the task is received and it is pending for available resources
STARTED – processing has started
SUCCESS – processing has completed successfully
FAILURE – processing failed
REVOKED – processing was cancelled by the user (or the system)
RETRY – the task execution failed due to internal reasons, the task is queued for re-execution (up to 3 times)

Each task is processed in sub-stages, for example, original language is first determined in a video, and then transcription is performed. In such cases, the video processing status may change from “STARTED” to “PENDING”, and back. This is due to waiting for resources for a specific processing sub-stage. In this case, the overall percentage “progress” of video processing will reflect the full picture.

The result data is stored for 1 month, after which it is deleted.

For billing conditions see the corresponding methods in /ai/ domain. The task is billed only after successful completion of the task and transition to “SUCCESS” status.

GET

streaming

tasks

{task_id}

Get AI task result

curl --request GET \
  --url https://api.gcore.com/streaming/ai/tasks/{task_id} \
  --header 'Authorization: <api-key>'

{
  "task_id": "aafe70c6-0000-0000-0000-327b65f7670f",
  "task_data": {
    "url": "https://demo-public.gvideo.io/videos/2675_TVKIqpTO7tEFoFg/qid5774v1_h264_450_360.mp4",
    "category": "sport",
    "client_id": 2675,
    "task_name": "content-moderation"
  },
  "progress": 100,
  "status": "SUCCESS",
  "processing_time": {
    "started_at": "2024-07-13T12:30:00.000Z",
    "completed_at": "2024-07-13T12:31:02.900Z",
    "total_time_sec": 62.901
  },
  "result": {
    "sport_detected": true,
    "detection_results": [
      "shooting goal (soccer)",
      "playing cricket"
    ],
    "frames": [
      {
        "label": "shooting goal (soccer)",
        "frame_number": 68,
        "confidence": 1
      },
      {
        "label": "playing cricket",
        "frame_number": 728,
        "confidence": 0.99
      }
    ]
  }
}

Authorizations

Authorization

string

header

required

API key for authentication. Make sure to include the word apikey, followed by a single space and then your token. Example: apikey 1234$abcdef

Path Parameters

task_id

string

required

ID of the task to get status of execution or result. This value is taken from the response of the initial AI task creation method.

Response

Result of AI task execution

task_id

string<uuid>

required

ID of the AI task

status

enum<string>

required

Status of processing the AI task. See GET /ai/tasks/{task_id} method for description.

Available options:

PENDING,

STARTED,

SUCCESS,

FAILURE,

RECEIVED,

REVOKED,

RETRY

progress

integer

required

Percentage of task completed. A value greater than 0 means that it has been taken into operation and is being processed.

processing_time

object

required

Show child attributes

task_data

AI transcription task data · object

required

The object will correspond to the task type that was specified in the original request. There will be one object for transcription, another for searching for nudity, and so on.

AI transcription task data
AI Content Moderation NSFW task data
AI Content Moderation hard nudity task data
AI Content Moderation soft nudity task data
AI Content Moderation sport task data

Show child attributes

Example:

{
  "url": "https://demo-files.gvideo.io/apidocs/spritefright-blender-cut30sec.mp4",
  "task_name": "transcription",
  "audio_language": "ger"
}

result

object

Show child attributes

Example:

{
  "concatenated_text": "Come on team, we mustn't dilly dally when there's so much nature to see!  I was thinking, we should call our class project, Fungi in a Forest!",
  "subtitles": [
    {
      "start_time": "00:00:00.009",
      "end_time": "00:00:03.689",
      "text": "Come on team, we mustn't dilly dally when there's so much nature to see!"
    },
    {
      "start_time": "00:00:04.129",
      "end_time": "00:00:08.169",
      "text": "I was thinking, we should call our class project, Fungi in a Forest!"
    }
  ],
  "vttContent": "WEBVTT 1 00:00:00.009 --> 00:00:03.689 Come on team, we mustn't dilly dally when there's so much nature to see!\n2 00:00:04.129 --> 00:00:08.169 I was thinking, we should call our class project, Fungi in a Forest!",
  "languages": ["eng"]
}

Create AI-task Cancel AI task

⌘I