ae_transcribe_video
Transcribe video or audio files with word-level timestamps, saving JSON transcripts for use in removing filler words and stutters during editing.
Instructions
Transcribe a video/audio file with timestamps (segments + word-level when available). Saves JSON under ~/.ae-mcp/transcripts/. Requires Python + faster-whisper (or openai-whisper) and ffmpeg. Use result with ae_transcript_to_cuts for filler/stutter removal edits.
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": {
"path": "<path>"
},
"name": "ae_transcribe_video"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Absolute path to video or audio | |
| model | No | Whisper model: tiny|base|small|medium|large-v3 | base |
| language | No | Optional language code e.g. en, ja. Auto-detect if omitted. |