aodianyun/ocrsrt | API reference

Public

19 runs

Run aodianyun/ocrsrt with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field	Type	Default value	Description
video	string		Input video file or URL
region	string		Subtitle region (format: x_min,y_min,x_max,y_max, e.g., 0,900,1920,1080)
center_point	string		Center point coordinate (format: x,y, e.g., 960,1000). Only extract subtitles near this point
min_score	number	0.7 Max: 1	Minimum OCR confidence threshold
similarity	number	0.7 Max: 1	Text similarity threshold for merging subtitles
match_mode	None	contain	Region matching mode
target_height	number		Target subtitle font height in pixels (also used as center-radius)
height_threshold	number	0.2 Max: 1	Font height difference threshold (ratio)

{
  "type": "object",
  "title": "Input",
  "required": [
    "video",
    "region"
  ],
  "properties": {
    "video": {
      "type": "string",
      "title": "Video",
      "format": "uri",
      "x-order": 0,
      "description": "Input video file or URL"
    },
    "region": {
      "type": "string",
      "title": "Region",
      "x-order": 1,
      "description": "Subtitle region (format: x_min,y_min,x_max,y_max, e.g., 0,900,1920,1080)"
    },
    "min_score": {
      "type": "number",
      "title": "Min Score",
      "default": 0.7,
      "maximum": 1,
      "minimum": 0,
      "x-order": 3,
      "description": "Minimum OCR confidence threshold"
    },
    "match_mode": {
      "enum": [
        "overlap",
        "contain",
        "center"
      ],
      "type": "string",
      "title": "match_mode",
      "description": "Region matching mode",
      "default": "contain",
      "x-order": 5
    },
    "similarity": {
      "type": "number",
      "title": "Similarity",
      "default": 0.7,
      "maximum": 1,
      "minimum": 0,
      "x-order": 4,
      "description": "Text similarity threshold for merging subtitles"
    },
    "center_point": {
      "type": "string",
      "title": "Center Point",
      "x-order": 2,
      "nullable": true,
      "description": "Center point coordinate (format: x,y, e.g., 960,1000). Only extract subtitles near this point"
    },
    "target_height": {
      "type": "number",
      "title": "Target Height",
      "x-order": 6,
      "nullable": true,
      "description": "Target subtitle font height in pixels (also used as center-radius)"
    },
    "height_threshold": {
      "type": "number",
      "title": "Height Threshold",
      "default": 0.2,
      "maximum": 1,
      "minimum": 0,
      "x-order": 7,
      "description": "Font height difference threshold (ratio)"
    }
  }
}

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema

{
  "type": "string",
  "title": "Output"
}