transcript
Transcribe local media and edit timelines by spoken words instead of timecode, while removing filler words so cuts follow what was said.
Instructions
Transcribe source media locally and edit the timeline by what was SAID rather than by timecode. Also removes filler words. Actions: transcribe_media, edit_by_transcript, remove_filler_words, transcript_pack.
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": {
"action": "<action>"
},
"name": "transcript"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| args | No | Arguments for the chosen action, e.g. {"filepath": "/path/to/project.fcpxml"}. Any action that takes a filepath also accepts expected_sha256: the call refuses if the file no longer hashes to it (every write result and analyze_timeline report the current sha256). | |
| action | Yes | Which operation to run. |