add_caption_sequence
Add multiple timed text captions in sequence to create word-by-word TikTok-style captions, lyrics sync, or subtitle overlays.
Instructions
Add multiple timed text captions in sequence — perfect for word-by-word TikTok-style captions, lyrics sync, or subtitle-like overlays. Each caption has its own text, start time, and duration.
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": {
"captions": "<captions>",
"trackIndex": "<trackIndex>"
},
"name": "add_caption_sequence"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| scale | No | Scale percentage for all captions (default 100) | |
| captions | Yes | Array of caption objects with text, start time, and duration | |
| template | No | MOGRT template style (default: bold). Options: basic, bold, classic, modern, film, lower_third | |
| positionX | No | X position for all captions (0-1, default 0.5) | |
| positionY | No | Y position for all captions (0-1, default 0.75 = lower third area) | |
| trackIndex | Yes | Video track index for all captions |