Transcribe Speech
transcribeConvert speech from video or audio files into SRT subtitles locally. Generate subtitle files for captioning without cloud services.
Instructions
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.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"input": "<input>"
},
"name": "transcribe"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| input | Yes | Path to the video or audio to transcribe. | |
| model | No | Path to a whisper.cpp model file (ggml-*.bin). Defaults to SCREENCAST_WHISPER_MODEL. | |
| words | No | One word per cue, for word timing (cut_by_transcript). | |
| output | No | Optional output .srt path. Defaults under SCREENCAST_HOME/edits. | |
| language | No | Spoken language code, e.g. 'en', or 'auto' (default). | |
| overwrite | No | Allow replacing an existing file at the output path (default false). |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| cues | Yes | ||
| text | Yes | ||
| srtPath | Yes |