SCREENCAST-MCP / TOOLS / AUDIO
Narrate
narrate
Offline voiceover with the built-in Windows voices: speaks each line at its time or marker over the audio, plus an SRT.
audiowritesdestructivesince v0.47.0
00:00PARAMETERS
| Name | Type | Description |
|---|---|---|
video required | string | Path to the video. |
lines required | object[] | at least 1 items |
lines[].t | number | Seconds. ≥ 0 |
lines[].marker | string | Or a marker label. |
lines[].text required | string | |
voice | string | Voice name or part (doctor lists them). |
rate | number | Default 1. ≥ 0.5, ≤ 3 |
duck | boolean | Duck the original audio (default true). |
output | string | Optional output path. Defaults under SCREENCAST_HOME/edits. |
overwrite | boolean | Allow replacing an existing file at the output path (default false). |
00:05A MINIMAL CALL
narrate { "video": "recording.mp4", "lines": [{"text": "Save"}] }
The required arguments only, with placeholder values. Everything else takes its default.
00:10WHAT COMES BACK
Structured content (structuredContent), alongside a text summary:
| Field | Type | Description |
|---|---|---|
outputPath always | string | Path of the file written. |