Command · Who Speaks When
analysis.speakers
Active-speaker detection for a multicam source, on this computer: who speaks when (with crosstalk, silence and laughter) and which angle shows whom (close-up or wide), from the transcripts with their speakers, each angle's microphone level and each camera's faces and lip motion.
- v1
- Capability MediaAnalysis
- Tool
analysis_speakers
Request
{
"command": "analysis.speakers",
"params": {}
}Parameters
anglesobject[]- Your angle assignments; they win over the guesses.
angles[].angleinteger (1..64)Required- The angle (1 = the first).
angles[].role`closeUp` | `wide` | `unknown`- What it shows.
angles[].speakerstring- Whom a close-up shows: a speaker's key or name (analysis.speakers lists them).
clipinteger (1..)- A multicam clip of the sequence (default: its first).
facesboolean- Look at the cameras' faces (default true; false is quicker on long recordings: the angles' roles then come from your assignments and the microphones).
multicaminteger (1..)- Or the multicam source sequence itself.
segmentsinteger (0..100000)- At most this many segments listed (default 400).
sequenceinteger (1..)- Sequence id; only needed when the project has several.
Discussion
Active-speaker detection for a multicam source, on this computer: who speaks when (with crosstalk, silence and laughter) and which angle shows whom (close-up or wide), from the transcripts with their speakers, each angle's microphone level and each camera's faces and lip motion. Nothing changes. "angles" sets angles yourself; they win over the guesses.
Run it with wabcut-cli cmd <project> --json, from an MCP client as analysis_speakers, or from an extension. See Edit commands for requests, references and results.
See also
analysis.*
- analysis.detectBeats
Detect Beats. Finds the tempo and beats of a clip's music: beat markers labelled 1-2-3-4 (downbeats red) and the sequence's beat grid (snapping, edit.snapToBeats and edit.cutToBeats use it).
- analysis.detectShots
Detect Shots. Finds the cuts (hard cuts, fades through black, dissolves; flashes are not cuts) in a clip's video and, for a clip, marks them with sequence markers ("markers": false to only list them).
- analysis.subjects
Find Subjects. Finds the faces, people and salient regions of a media item over time, shot by shot (5-10 samples a second, denser while the picture moves; faces and people tracked within each shot).