analyze
Extracts word-level transcripts, face positions, shot boundaries, and beat times from a video asset to support captions, reframing, and beat-synced edits; returns a jobId.
Instructions
Analyse an asset. transcript = word-level speech-to-text (clip picking, captions, silence removal); faces = face positions (auto-face / split reframing); scenes = shot boundaries; beats = music tempo + beat times (beat-synced cuts). Cached; returns a jobId.
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": {
"assetId": "<assetId>",
"include": "<include>"
},
"name": "analyze"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| wait | No | ||
| force | No | ||
| model | No | Whisper model override, e.g. small, medium, large-v3-turbo | |
| prompt | No | Names or terms to help transcription spell things right | |
| assetId | Yes | ||
| include | Yes | ||
| language | No | ISO code like en, hi, pa; omit to auto-detect |