transcribe_and_caption
Transcribes video audio to text with word-level timing and creates ASS captions. Optionally burns captions into a new render using brand, karaoke, or minimal styles.
Instructions
ASR word timeline + ASS captions; optionally burn into a new render (brand|karaoke|minimal).
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": {
"project_id": "<project_id>"
},
"name": "transcribe_and_caption"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| burn | No | ||
| style | No | brand | |
| language | No | ||
| model_size | No | base | |
| project_id | Yes | ||
| fallback_transcript | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||