Operator for generating product voice-over and storyboard based on reference videos, designed for e-commerce short video creation scenarios. The operator jointly analyzes the reference video, target product images, and optional natural language requirements to generate a standard storyboard package that can be directly handed off to downstream text-to-video workflows.

Operator ID: las_video_storyboard_gen

Applicable scenarios #

Core capabilities #

• Jointly analyzes reference video visuals, voice-over, and target product images to identify the product's core purpose, intended users, and visible selling point evidence.
• Supports reference storyboard, script, selling points, hooks, or free fusion, and allows specification of creative focus via user_prompt.
• By default, generates up to N+1 candidate sets, where N is the number of input videos; partial candidates may be accepted, but at least one structurally usable result is returned.
• Each candidate set includes a complete voice-over, fully readable storyboard, structured shot-by-shot description, as well as generation rationale and creative notes.
• Output aligns with the standard storyboard bundle protocol and can be further processed by text-to-video or other downstream storyboard workflows.

Supported regions #

• Beijing: cn-beijing
• Shanghai: cn-shanghai
• Guangzhou: cn-guangzhou

Operator performance #

Input requirements #

Output requirements #

• Billing standards

  Sub-items	Billing standards description
  Billing item	Includes two billing items: Basic invocation fee and Video Storyboard Gen - video understanding. The actual charge is the sum of the fees for both billing items. Base invocation fee: The operator invocation fee incurred each time the operator is called. Video Storyboard Gen - video understanding: The fee incurred when the operator generates a Video Storyboard Gen. This portion of the fee is calculated based on the duration of the input video, and during billing, the billing duration is converted according to a certain coefficient based on the operator model tier (request parameter model_tier) used.
  Billing type	Usage-based billing, with charges posted hourly based on actual usage. Billing precision: millisecond-level precision, rounded to the nearest millisecond
  Unit price	The unit prices for Basic invocation fee and Video Storyboard Gen - video understanding are different. For details, see the table below.

• Billing details
  Billing formula: Total cost = Base invocation fee + Video Storyboard Gen fee = 1 CNY + Video Storyboard Gen-coefficient base fee unit price * total input video duration * billing duration conversion coefficient

  Billing item	Unit price	Operator model tier	Billing duration conversion coefficient
  Base invocation fee	1 CNY/call	Not applicable	Not applicable
  Video Storyboard Gen - video understanding	1.5 CNY/minute	Standard version Request parameter model_tier set to standard	1
  		Enhanced version Request parameter model_tier set to pro	2

• Billing example
  When 3 reference videos, each 1 minute long, are input and the operator's model tier is set to pro (enhanced version):

  • The duration conversion coefficient is: 2.
  • The actual cost is:
    Cost = 1 CNY + 1.5 CNY/minute * 1 minute * 3 * 2 = 10 CNY

API invocation instructions #

• The operator's API is an asynchronous task interface. You need to submit a task via the submit interface, then use the Poll interface to check the task status and obtain the operator's processing results. Additionally, the operator supports asynchronous callback capability (Callback). You can set the callback parameter callback.url when initiating the operator task. LAS will send an HTTP POST notification to this URL. For guidance on using asynchronous callbacks, refer to Asynchronous callback API.
• Caution: After a task is submitted, the task_id is valid for 3 days. After 3 days, the task_id cannot be used to retrieve the operator's processing result.

Submit #

Interface instructions #

Submit an asynchronous task to generate product voice-over and storyboard based on reference videos. The operator analyzes the reference video and target product images to generate multiple sets of standard voice-over scripts.

Request parameters #

Response parameters #

Example #

Request example

export OUTPUT_TOS_PATH="tos://path/to/video_storyboard_gen_results"

curl --location "https://operator.las.cn-beijing.volces.com/api/v1/submit" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer $LAS_API_KEY" \
--data '{
  "operator_id": "las_video_storyboard_gen",
  "operator_version": "v1",
  "data": {
    "video_urls": [
      "https://${LAS_TOS_BUCKET}.${TOS_ENDPOINT}/operator_cards_serving/public/${LAS_ENVIRONMENT}/las_video_storyboard_gen/v1/input_video_01.mp4",
      "https://${LAS_TOS_BUCKET}.${TOS_ENDPOINT}/operator_cards_serving/public/${LAS_ENVIRONMENT}/las_video_storyboard_gen/v1/input_video_02.mp4"
    ],
    "product_image_urls": [
      "https://${LAS_TOS_BUCKET}.${TOS_ENDPOINT}/operator_cards_serving/public/${LAS_ENVIRONMENT}/las_video_storyboard_gen/v1/input_image_01.png"
    ],
    "user_prompt": "请展示割草机好用耐造，适用各种场景。",
    "output_tos_path": "$OUTPUT_TOS_PATH"
  }
}'

Response example

{
  "metadata": {
    "task_id": "task-20260812150000-abc123",
    "task_status": "PENDING",
    "business_code": "0",
    "error_msg": ""
  }
}

Error codes #

Poll #

Interface instructions #

Query the status and results of tasks for generating product voiceovers and storyboards from reference videos.

Request parameters #

Response parameters #

Examples #

Request example

curl --location "https://operator.las.cn-beijing.volces.com/api/v1/poll" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer $LAS_API_KEY" \
--data '{
  "operator_id": "las_video_storyboard_gen",
  "operator_version": "v1",
  "task_id": "task-20260812150000-abc123"
}'

Response example

{
  "metadata": {
    "task_id": "task-20260812150000-abc123",
    "task_status": "COMPLETED",
    "submit_time": "2026-08-12T15:00:00+08:00",
    "end_time": "2026-08-12T15:06:00+08:00",
    "business_code": "0",
    "error_msg": ""
  },
  "data": {
    "result_urls": [
      "tos://bucket/output/runs/run_x/variants/variant_001/storyboard_bundle_manifest.json"
    ]
  }
}

Error codes #