SCREENCAST-MCP / TOOLS / AUDIO
Transcribe Speech
transcribe
Transcribe a recording's speech to an SRT subtitle file, locally, with FFmpeg 8's whisper filter (needs a whisper.cpp model file). Returns the SRT path and the text. Pair with burn_subtitles to caption the video.
audiowritesdestructivesince v0.25.0
00:00PARAMETERS
| Name | Type | Description |
|---|---|---|
input required | string | Path to the video or audio to transcribe. |
model | string | Path to a whisper.cpp model file (ggml-*.bin). Defaults to SCREENCAST_WHISPER_MODEL. |
language | string | Spoken language code, e.g. 'en', or 'auto' (default). |
words | boolean | One word per cue, for word timing (cut_by_transcript). |
output | string | Optional output .srt path. Defaults under SCREENCAST_HOME/edits. |
overwrite | boolean | Allow replacing an existing file at the output path (default false). |
00:05A MINIMAL CALL
transcribe { "input": "recording.mp4" }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 |
|---|---|---|
srtPath always | string | |
cues always | integer | ≥ -9007199254740991, ≤ 9007199254740991 |
text always | string |
00:15SEEN IN