ocr_region
Extract text from a video frame region in reading order, returning each line's text and bounding box. Use it to capture on-screen captions or subtitles.
Instructions
Read all text lines in region at t -> {t,lines:[{text,box}]} in reading order.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"video": "<video>",
"t": "<t>"
},
"name": "ocr_region"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| t | Yes | time in s | |
| video | Yes | video path (relative to workdir ok) | |
| region | No | [x0,y0,x1,y1] source px; null=full frame |