Docs

Lake AI Service

Video generation

Short drama narration

The short drama narration operator is designed for short dramas, film clips, and plot-driven content. It can automatically perform original video ASR, video understanding, viral narration script generation, TTS narration, subtitle generation, and video rendering based on a single input video, outputting a new video with narrated voice-over. This is suitable for short drama promotion, remixing film and television content, and batch content production.

Operator introduction

Operator ID: las_short_drama_narration_gen

Applicable scenarios

Short drama promotion content generation: Automatically processes short drama clips into promotional materials with narrated voice-over, enhancing content comprehension efficiency and opening appeal.
Remixing film and television content: Generates plot narration, clarification of character relationships, and key conflict descriptions based on film clips, reducing manual scriptwriting and narration costs.
Batch content production: In conjunction with upstream editing tools or content libraries, generates narrated versions for multiple candidate clips individually, for distribution, review, or A/B testing.
Plot review: Helps content managers quickly understand the storyline and communication points of materials through automatically generated narrated videos.

Core capabilities

Video content understanding: Automatically analyzes the input video’s visuals, plot progression, character relationships, and key events to provide contextual basis for narration script generation.
Original video ASR recognition: Automatically recognizes dialogue and audio content in the original video, assisting in determining plot information and identifying highlight original audio segments that can be retained.
Viral narration script generation: Supports controlling narration style via style_prompt, with the default generating a tightly paced short drama narration script that hooks the audience early and avoids spoiling key plot twists.
Pause density control: Supports four levels of pause density—none, low, medium, and high—to control the proportion of narration coverage and the degree of highlight retention from the original video.
TTS narration and time alignment: Automatically synthesizes the narration script into speech and aligns it with the video time window, ensuring the narration pacing matches the visual content. Currently, Chinese narration generation is supported, and the narration voice uses the default preset template.
Subtitle and video rendering: Automatically generates narration subtitles and completes video rendering, outputting the final video with voice-over and subtitles.

Effect demonstration

Input video

Output video

The current example uses a medium narration pause.

Supported regions

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

Operator performance

Sub-items	Performance impact description
Maximum RPM	600
Maximum concurrency	10
Processing time	Processing time is directly proportional to the input video duration (the longer the video, the higher the time required for understanding, narration generation, and audio synthesis). The ratio is approximately 1 to 5 (a 1-minute video takes about 5 minutes to generate the corresponding narrated video).

Input and output requirements

Input requirements

Details	Detailed requirements
Supported input data modalities	Video
Input format: Video	Formats: `mp4`, `mov`, `avi`, `mkv`, `flv`, `webm`, `m4v`. Quantity: Process 1 video per request. Size: Input video duration must be at least 20 seconds and up to 5 minutes; input video size must not exceed 500 MB.
Input path requirements	Provide input data to the operator via the request parameter `video_url`. Currently, two methods are supported: public URL and TOS path. Public URL: A video URL accessible via the public internet, format is `http/https`. Public URLs do not support addresses requiring login status or additional header authentication; temporary URLs must be valid during task execution. TOS path: After uploading the data to be processed to a TOS bucket under the same primary account and region as the current LAS service, you can provide a TOS path in the format `tos://bucket_name/demo`. The TOS object must exist and have read permissions.

Details

Detailed requirements

Supported input data modalities

Video

Input format: Video

Formats: mp4, mov, avi, mkv, flv, webm, m4v.
Quantity: Process 1 video per request.
Size: Input video duration must be at least 20 seconds and up to 5 minutes; input video size must not exceed 500 MB.

Input path requirements

Provide input data to the operator via the request parameter video_url. Currently, two methods are supported: public URL and TOS path.

Public URL: A video URL accessible via the public internet, format is http/https.
- Public URLs do not support addresses requiring login status or additional header authentication; temporary URLs must be valid during task execution.
TOS path: After uploading the data to be processed to a TOS bucket under the same primary account and region as the current LAS service, you can provide a TOS path in the format tos://bucket_name/demo.
- The TOS object must exist and have read permissions.

Output requirements

Details	Detailed requirements
Output data modalities	Video
Output format: Video	Format: Unified output in `mp4` format The original video's duration, resolution, and other properties are not changed
Output path: TOS	Specify the storage path for the operator's output result using the request parameter `output_tos_path`. Currently, setting a TOS path is supported. TOS path: A writable TOS Bucket directory under the same primary account and region as the LAS service, format: `tos://bucket/output/`.

Details

Detailed requirements

Output data modalities

Video

Output format: Video

Format: Unified output in mp4 format
The original video's duration, resolution, and other properties are not changed

Output path: TOS

Specify the storage path for the operator's output result using the request parameter output_tos_path. Currently, setting a TOS path is supported.

TOS path: A writable TOS Bucket directory under the same primary account and region as the LAS service, format: tos://bucket/output/.

Billing instructions

Billing standards

Sub-items	Billing standards description
Billing item	Billing is calculated based on the duration of the input video.
Billing type	Usage-based billing, unit: `CNY/minute`, billed hourly based on actual usage.
Unit price	1.5 CNY/minute

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

Caution and prerequisites

Details	Caution and prerequisites
Costs	Before calling an operator, you need to understand the model invocation costs associated with using the operator. For details, see Large model invocation billing.
Authentication (API Key)	Before calling an operator, you need to generate an API Key for operator invocation. It is recommended to configure the API Key as an environment variable to ensure safer operator calls. For details, see Obtain and configure API Key.
BaseURL	Before calling an operator, you need to determine the BaseURL for operator invocation based on the region where your current LAS service is deployed. This is used to configure the path parameter values for operator calls. For details, see Obtain the Base URL. The Examples below are for reference only; when making actual calls, replace the path values with those corresponding to your region.

Rest API call

Submit

Interface description

Submit a task to generate narration for short drama materials. After successful submission, a task ID is returned. The final video can be obtained through the query interface.

Request parameters

Name	Type	Required	Example value	Description
operator_id	string	Yes	las_short_drama_narration_gen	Operator ID
operator_version	string	Yes	v1	Operator version
data	ShortDramaNarrationGenInfo	Yes		Short drama material narration generation request parameters

Response parameters

Name	Type	Example value	Description
metadata	metadata		Request metadata

Example

Request example

# Please set OUTPUT_TOS_PATH to a writable tos path under your account, and ensure the TOS bucket region matches the operator BaseURL region
export OUTPUT_TOS_PATH="tos://bucket/output/"

curl --location "https://las.ap-southeast-1.volces.com/api/v1/submit" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer $LAS_API_KEY" \
--data '{
    "operator_id": "las_short_drama_narration_gen",
    "operator_version": "v1",
    "data": {
        "video_url": "https://example.com/input.mp4",
        "output_tos_path": "$OUTPUT_TOS_PATH",
        "style_prompt": "短剧爆款解说，节奏紧凑，开头先抛出悬念，不剧透关键反转。",
        "blank_density": "medium"
    }
}'

Response example

{
  "metadata": {
    "task_id": "20260606_150000_abc123",
    "task_status": "PENDING",
    "business_code": "0",
    "error_msg": ""
  }
}

Error codes

HttpStatusCode	Error code	Error message	Description
400	Parameter.Invalid	invalid parameter	Invalid parameter, such as an invalid enumeration value, out-of-range numeric parameter, and so on.
400	Parameter.Missing	Missing required parameter	Missing required parameter, such as `video_url`, or missing customer TOS credentials in TOS read/write scenarios.
400	Url.Invalid	invalid url	Video URL cannot be accessed, protocol not supported, or path is invalid.
400	Video.Invalid	invalid video file	Invalid video file, such as no video stream, empty file, or unable to parse duration.
400	Video.DownloadFailed	Video download failed	Video download error or access failure.
400	Video.FormatUnsupported	Video format not supported	Video format not supported.
400	Video.DurationTooShort	Video duration is too short	Video duration is too short, less than 20 seconds.
400	Video.DurationExceeded	Video duration exceeds maximum limit	Video duration exceeds the limit, more than 5 minutes.
400	Video.FileTooLarge	Video file is too large	Video file is too large, more than 500 MB.
400	Video.Timeout	Video processing timeout	Video processing timed out.
400	Video.UploadFailed	Video upload failed	Result upload failed.
400	Video.ModelFailed	VLM call failed	Video understanding or model call failed.
400	Tos.AccessFailed	Failed to access TOS path with provided credentials	Failed to access TOS path or credentials are invalid.
400	Connection.TooMany	Too many connections	Concurrency is too high, triggering rate limiting.
401	Authorization.Missing	Missing Authorization.	Authorization is missing.
401	ApiKey.InValid	The api key is invalid.	API Key is invalid.
500	InternalError	Internal error	Internal service error.

Poll

Interface description

Query the execution status and result of the short drama material narration generation task. The final video can be obtained after the task is completed.

Request parameters

Name	Type	Required	Example value	Description
operator_id	string	Yes	las_short_drama_narration_gen	Operator ID
operator_version	string	Yes	v1	Operator version
task_id	string	Yes	task-xxx	Task ID

Response parameters

Name	Type	Example value	Description
metadata	metadata		Metadata of the request
data	ShortDramaNarrationGenResponse		Returned data

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_short_drama_narration_gen",
    "operator_version": "v1",
    "task_id": "20260606_150000_abc123"
}'

Response example

{
  "metadata": {
    "task_id": "20260606_150000_abc123",
    "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": ""
  },
  "data": {
    "final_video_path": "tos://bucket/output/final.mp4",
    "final_video_url": "https://example.com/final.mp4",
    "status": "success"
  }
}

Error codes

HttpStatusCode	Error code	Error message	Description
400	Parameter.Invalid	invalid parameter	Parameter is invalid.
400	Parameter.Missing	Missing required parameter	Required parameter is missing.
400	Url.Invalid	invalid url	Video URL is inaccessible, protocol not supported, or path is invalid.
400	Video.Invalid	invalid video file	Video file is invalid.
400	Video.DownloadFailed	Video download failed	Video download exception or access failed.
400	Video.FormatUnsupported	Video format not supported	Video format not supported.
400	Video.DurationTooShort	Video duration is too short	Video duration is too short.
400	Video.DurationExceeded	Video duration exceeds maximum limit	Video duration exceeds the limit.
400	Video.FileTooLarge	Video file is too large	Video file is too large.
400	Video.Timeout	Video processing timeout	Video processing timed out.
400	Video.UploadFailed	Video upload failed	Result upload failed.
400	Video.ModelFailed	VLM call failed	Video understanding or model call failed.
400	Tos.AccessFailed	Failed to access TOS path with provided credentials	Failed to access TOS path or credentials are invalid.
400	Connection.TooMany	Too many connections	Concurrency is too high, triggering rate limiting.
401	Authorization.Missing	Missing Authorization.	Authorization is missing.
401	ApiKey.InValid	The api key is invalid.	API Key is invalid.
500	InternalError	Internal error	Internal service error.

Last updated: 2026.07.28 16:13:06

Lake AI Service

Applicable scenarios #

Core capabilities #

Effect demonstration #

Supported regions #

Operator performance #

Input requirements #

Output requirements #

Submit #

Interface description #

Request parameters #

Response parameters #

Example #

Request example #

Response example #

Error codes #

Poll #

Interface description #

Request parameters #

Response parameters #

Example #

Request example #

Response example #

Error codes #

Applicable scenarios

Core capabilities

Effect demonstration

Supported regions

Operator performance

Input requirements

Output requirements

Submit

Interface description

Request parameters

Response parameters

Example

Request example

Response example

Error codes

Poll

Interface description

Request parameters

Response parameters

Example

Request example

Response example

Error codes