Command · Use Take
takes.use
Makes the sequence say a line once, with the chosen take: other takes of it on the timeline are removed with their pause, and a take that is not on the timeline replaces the first one there (linked video and audio, with small handles; what follows moves to fit).
- v1
- Capability EditSequence
- Tool
takes_use
Request
{
"command": "takes.use",
"params": {
"best": true
}
}Parameters
acrossRecordingsboolean- Attempts in different recordings count (default true).
bestboolean- Use the best take of every group ("Keep best takes").
groupinteger (1..)- The group of takes, 1-based as takes.find lists them (with the same options).
includeSourceMediaboolean- Also look in the whole recordings the sequence uses, for takes trimmed away (default true).
maxGapnumber (1.0..36000.0)- Within one recording, attempts further apart than this (seconds) are not retakes (default 180).
meaningboolean- Also group paraphrased attempts by meaning with the text encoder (slower; default false).
media(integer | string (1..))[], min 1- More media items whose transcripts hold takes.
minSimilaritynumber (0.3..1.0)- How alike two attempts must be to count as takes of one line, 0.3..1 (default 0.7).
sequenceinteger (1..)- The sequence; only needed when the project has several.
takeinteger (1..)- The take to use, 1-based (default 1: the best).
Discussion
Makes the sequence say a line once, with the chosen take: other takes of it on the timeline are removed with their pause, and a take that is not on the timeline replaces the first one there (linked video and audio, with small handles; what follows moves to fit). "best": true does this for every group whose best take is not already the one heard. Pass the same options as takes.find (and its expectedRevision). One undo step; returns the review list.
Run it with wabcut-cli cmd <project> --json, from an MCP client as takes_use, or from an extension. See Edit commands for requests, references and results.
See also
takes.*
- takes.find
Find Takes. Finds repeated attempts of the same line (retakes and false starts) in a sequence and the recordings it uses: groups of takes, best first, each with its words, a word-by-word difference from the best one, and quality (fillers, false starts, pauses, complete sentence, level, clipping, noise floor, pace).