The Subtitle Erase Pro operator automatically detects and removes embedded hard subtitles from video frames, and outputs the video file after erasure. This operator is suitable for erasing subtitles in videos with vertical white subtitles. Compared to the standard edition, it delivers better results after erasure, does not leave noticeable blur, accurately reconstructs background textures, and restores the original video frame to a greater extent. It is ideal for scenarios with extremely high image quality requirements, such as overseas distribution of short dramas and professional derivative works.

Operator ID: las_subtitle_erase_pro

Core capabilities #

• Intelligent automatic detection and removal of embedded subtitle regions in video frames.
• Supports erasure of specified regions: precisely specify the region to be erased using proportional coordinates.
• High-quality, seamless erasure that retains more details, does not leave noticeable blur, and delivers higher image quality.
• Supports Subtitle / Text erasure modes, covering both subtitles and on-screen text.
• Supports Quality / Size output encoding strategies, balancing image quality and file size.
• Asynchronous task processing. Results are obtained by polling after submission.

Effect showcase #

Supported regions #

• Beijing: cn-beijing

Operator performance #

Input requirements #

Output requirements #

• Billing standard

  Item breakdown	Billing standard description
  Billing item	Billing is based on the duration of the output video.
  Billing type	Usage-based billing, unit: CNY/minute, billed hourly based on actual usage.
  Unit price	1.0 CNY/minute

• Billing details
  Billing formula: Total cost = unit price * usage

Submit #

API description #

Use the Subtitle Erase Pro operator to submit an erasure task, automatically detect and remove embedded hard subtitles from video frames, and supports specifying the erasure region. This is an asynchronous API. Upon successful submission, task_id is returned. Use the Poll API to query the task status and results.

Request parameters #

Response parameters #

Example #

Request example

curl --location "https://operator.las.ap-southeast-1.volces.com/api/v1/submit" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer $LAS_API_KEY" \
--data '{
    "operator_id": "las_subtitle_erase_pro",
    "operator_version": "v1",
    "data": {
        "video_url": "https://example.com/input.mp4",
        "client_token": "550e8400-e29b-41d4-a716-446655440000",
        "mode": "Subtitle",
        "output_encode_mode": "Quality",
        "erase_ratio_location": [
            {
                "top_left_x": 0.05,
                "top_left_y": 0.80,
                "bottom_right_x": 0.95,
                "bottom_right_y": 0.98
            }
        ]
    }
}'

Response example

{
  "metadata": {
    "task_id": "las-task-xxxx",
    "task_status": "RUNNING",
    "business_code": "0",
    "error_msg": "",
    "request_id": "abcd1234"
  },
  "data": {}
}

Error codes #

Poll #

API description #

Query the execution status and results of the Subtitle Erase Pro task. When the task status is COMPLETED, the resulting video after erasure is returned.

Request parameters #

Response parameters #

Example #

Request example

curl --location "https://operator.las.ap-southeast-1.volces.com/api/v1/poll" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer $LAS_API_KEY" \
--data '{
    "operator_id": "las_subtitle_erase_pro",
    "operator_version": "v1",
    "task_id": "las-task-xxxx"
}'

Response example

{
    "metadata": {
        "task_id": "las-task-xxxx",
        "task_status": "COMPLETED",
        "submit_time": "2026-07-21T16:04:06+08:00",
        "end_time": "2026-07-21T16:04:06+08:00",
        "business_code": "0",
        "error_msg": "",
        "request_id": "abcd1234"
    },
    "data": {
        "video_url": "https://example.com/output.mp4",
        "duration": 12.34
    }
}

Error codes #