Marketplace/@admin/watch-video

Watch Video

Transcribe a YouTube (or other yt-dlp-supported) video to text using a local Whisper-tiny model. Runs entirely on CPU — no platform inference credits are spent.

jobmediav0.1.0Featured
Updated 3h ago · 5 total runs

Inputs

urlstringrequiredYouTube URL (or any URL yt-dlp can resolve) to transcribe.
model_sizestringWhisper model size. Larger = more accurate, much slower on CPU.
languagestringOptional BCP-47 hint for source language (e.g. "en", "ru"). Auto-detected when blank.

Outputs

textstring
languagestring
duration_secondsnumber
segment_countinteger
titlestring
transcript_pathstring
srt_pathstring

Resources

CPU
2
Memory
2048 MB
Timeout
1200s