plan_cuts
Builds a reviewable cut plan from silences, filler words, retakes, and manual transcript cuts, returning a planId and summary to approve before applying edits.
Instructions
Build a cut plan (which parts of the source to keep) from silences, filler words (um/uh…), retakes (restarted sentences) and your own manualCuts chosen from the transcript. Nothing is changed in the editor yet: returns a planId and a summary to review with the user, then call apply_cuts.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "plan_cuts"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | ||
| model | No | Whisper model. "base" (default) is fast; "small"/"medium"/"large-v3-turbo" are more accurate but slower. Downloaded on first use. | |
| minKeep | No | Drop kept pieces shorter than this, seconds (default 0.25) | |
| padding | No | Breathing room kept around speech at each cut, seconds (default 0.08) | |
| language | No | ISO language code such as "en" or "fr"; default auto-detect. | |
| manualCuts | No | Extra SOURCE-time ranges to remove | |
| minSilence | No | Shortest pause to remove, seconds (default 0.5) | |
| fillerWords | No | Override filler list, e.g. ["um","uh","you know"] | |
| thresholdDb | No | Silence threshold dBFS (default -35) | |
| removeFillers | No | Default true (needs a transcript; transcribes automatically) | |
| removeRetakes | No | Default false. Cuts earlier attempts when a sentence is restarted within ~10s. | |
| removeSilences | No | Default true |