transcript
Retrieve a media clip's timed speech-to-text segments in source seconds for clip assembly, with optional word-level timings; automatically generates text when missing.
Instructions
Get the transcription of a media clip as segments with start/end in SECONDS OF SOURCE (ready for clips_assemble in/out). words=true includes word-level timings. Transcribes first if needed.
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": {
"item": "<item>"
},
"name": "transcript"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| item | Yes | ||
| words | No | ||
| transcribe_if_missing | No |