Video Text Removal Create API

Last Updated: 2026-05-11

Video Text Removal

Service Overview

Creates a video text removal task. Submit source video and erase regions for asynchronous processing.

The Video Text Removal API uses a console-based project access model. You can register and activate services on the ViiTor AI official website (https://www.viitor.com/), then create a project in the console to obtain required authentication credentials.

The business service endpoint is provided by the project gateway. This document uses the following gateway as an example:

https://video-translation.ilivedata.com

Integration

Parameter Specification

Request URL: https://video-translation.ilivedata.com/textRemoval/add
Method: POST
Content-Type: application/json
Response Format: {code, message, data}

HTTP Headers

Header	Required	Type	Description
`Content-Type`	Yes	String	`application/json;charset=UTF-8`
`Accept`	Yes	String	`application/json;charset=UTF-8`
`Authorization`	Yes	String	Login token (Bearer Token)
`X-User-Id`	Yes	Long	User ID. The server overrides `userId` in request body.
`X-Channel`	Yes	Integer	Channel code: `100`=Web, `200`=Android, `300`=iOS
`X-App-Source`	No	String	Source marker, up to 20 characters

Notes:

The server uses X-User-Id, X-Channel, and X-App-Source from headers as the source of truth.

Request Method: POST

Request Body

Field Definitions

Field	Type	Required	Description
`url`	String	Yes	Source video URL (must be accessible)
`taskName`	String	Yes	Task name, truncated if longer than 50 characters
`textDetectROI`	Array<Array>	No	Text detection erase regions, e.g. `[[x1,y1,x2,y2], ...]`
`fullEraseROI`	Array<Array>	No	Full erase regions, e.g. `[[x1,y1,x2,y2], ...]`

Validation Rules

textDetectROI and fullEraseROI cannot both be empty.
Each ROI type supports up to 5 regions.

Response Body

Standard Response Schema

Field	Type	Description
`code`	Integer	`0` means success; non-zero means failure
`message`	String	Response message
`data`	Object	Business payload

`data` Fields on Success

Field	Type	Description
`userId`	Long	User ID
`taskId`	String	Task ID (used for status/result query)

Examples

cURL Request

curl -X POST "https://video-translation.ilivedata.com/textRemoval/add" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <TOKEN>" \
  -H "X-User-Id: 123456" \
  -H "X-Channel: 100" \
  -H "X-App-Source: official_web" \
  -d '{
    "url": "https://cdn.example.com/input/video.mp4",
    "taskName": "erase-subtitle-001",
    "textDetectROI": [[120, 640, 1180, 700]],
    "fullEraseROI": []
  }'

Success Response Example

{
  "code": 0,
  "message": "OK",
  "data": {
    "userId": 123456,
    "taskId": "ViiTor_AI_202605110001"
  }
}

Failure Response Example (Invalid Parameters)

{
  "code": 2001,
  "message": "Invalid Parameter",
  "data": null
}

Common Error Codes

Code	Meaning	Typical Cause
`2000`	Missing Parameter	Missing required Header or Body fields
`2001`	Invalid Parameter	Invalid params (e.g., empty `url/taskName`, invalid channel)
`10091`	insufficient points	User has insufficient points
`10093`	task creation failed	Internal task creation failure

Client Integration Recommendations

Call /textRemoval/add to obtain taskId.
Use taskId to poll task status endpoint.
Handle all code != 0 responses uniformly, especially parameter errors and insufficient points.