video-transcribe
Installation
SKILL.md
Video Transcribe
Download one video by URL and extract its spoken audio as text, or transcribe a
local media file. One script does both: scripts/transcribe.py.
Output (in the chosen folder): <basename>.txt (full text), <basename>.srt
(subtitles), <basename>.json (language, duration, model, and per-segment
timecodes).
Inputs
| Parameter | Required | Example |
|---|---|---|
| Video URL or local file path | yes | https://www.instagram.com/reels/DZScDIDNTi7/ |
--output-dir |
no | reference-reels/DZScDIDNTi7 |
--language |
no | es (default: auto-detect) |
--model |
no | small (default), medium, large-v3, tiny |