transcribe
Transcribe a local video or audio file to get every word with start and end times, plus SRT text and the engine used. Writes no file; use caption_video for captions or subtitles.
Instructions
Transcribes a local video or audio file and returns every word with its start and end time in seconds, plus the SRT text and the engine used. Writes no file: use caption_video when the user wants a captioned video, an overlay or a subtitle file. Needs a Creator or Pro key. engine "cloud" uses the plan's minutes and sends only compressed audio, deleted after transcription; "device" runs Whisper locally and uses none. Left unset, it picks cloud when the minutes left cover the file, else device.
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": "transcribe"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | The spoken language. Give it for any video that isn't in English; auto lets cloud transcription detect it. | |
| path | Yes | Absolute path to the video or audio file: MP4, MOV, WebM, MP3, WAV, M4A or another format the studio opens. | |
| engine | No | cloud: ElevenLabs Scribe on the plan's cloud minutes, strongest on music, accents and 90+ languages; the default when the minutes left cover the file. device: on-device Whisper, no minutes; the first run downloads the model (132 MB). | |
| keyterms | No | Names and words for cloud transcription to spell your way. |