domains / families / media / review-ugc-render

review-ugc-render

separate

Mandatory pre-publish review gate for a UGC video render. Transcribes the finished render's AUDIO with Whisper and word-diffs it against the approved spoken script, then gates keeping the render as the final version (video_review) — blocking a render whose generated audio mis-voices a word (e.g. the approved "human-vetted" spoken as "human witted"), says a different number or brand name, flips a negation, drops an approved phrase, or comes back silent. Correct speech written differently ("5mg" said "five milligrams", "30%" said "thirty percent", a spoken URL, "don't" said "do not", "larkfieldstraps" said "larkfield straps", a confirmed pronunciation like "TG1" said "T G one") passes. Runnable, gating counterpart to GooseWorks' fuller transcript-integrity review. Every ugc-video-formats recipe runs this after render and BEFORE keeping the final version.

When to use

• pre-publish review gate for UGC video render
• transcribe finished render audio with Whisper
• word-diff audio against approved spoken script
• gate keeping render as final version
• detect mis-voiced words, numbers, or brand names
• detect flipped negations or dropped phrases
• detect silent renders
• validate confirmed pronunciations

When not to use

• eyeball /watch review
• fuzzy matching
• publishing without passing the gate
• running without ffmpeg on PATH

Skill page

Source