video-use-best-practices
video-use Best Practices (Hebrew)
Problem
video-use ships with a strong English-first default: the bundled SUB_FORCE_STYLE uses Helvetica (no Hebrew glyphs, renders as boxes), 2-word UPPERCASE chunks (Hebrew has no uppercase), and the filler-removal step assumes an English filler lexicon while Scribe itself does not tag fillers per-word in any language. Hebrew creators using video-use hit the same three walls every time: missing-glyph boxes burned into the final video, captions that look wrong because UPPERCASE doesn't exist in Hebrew, and a "filler removal" step that leaves "אֶה", "כאילו", "יעני", and friends in. On macOS there's also a fourth wall: libass + SRT BiDi reordering is unreliable even with a fully-built libass, so Hebrew sentences render as characters drawn left-to-right in source byte order rather than in proper RTL visual order. This skill is the Hebrew-specific override layer on top of video-use's 12 Hard Rules. None of the upstream rules change, only the style values, font fallback chain, filler lexicon, caption-burn recipe, and self-eval frame checks.
Pricing you should understand before you start
video-use is free; underlying services are paid. Mode determines cost.
| Mode | What | Best for | Cost / 1hr video |
|---|---|---|---|
A. Captions-only (scripts/captions-only.sh) |
Transcribe + burn Hebrew captions on original. No cuts. | Lectures, webinars, podcast videos. | ~$1-3 total |
| B. Full cut (default video-use flow) | Inventory → strategy → cut → render → self-eval. | Teaser from raw footage; multi-take selection. | ~$25-60 (1hr); $120-300 (3hr). Scales super-linearly. |
Per-unit: Scribe ~$0.40/hr (paid) is an upper bound, ElevenLabs cut Scribe pricing ~40% in March 2026 (verify at the pricing page); current model is Scribe v2 (Jan 2026). Claude tokens depend on mode. Local FFmpeg/libass rendering is $0.
Free-tier reality check (the "$1-3" assumes paid Starter, $5/mo). ElevenLabs free tier is 10,000 credits/month, and Speech-to-Text bills ~330 credits/minute (the per-character figure is for text-to-speech, not STT), so it covers only ~30 minutes of transcription/month. A 10-minute Hebrew talking-head uses ~3,300 credits; gap-recovery (Step 8) re-transcribes dropped windows, counting again. So free tier yields two or three short videos/month before the quota wall. Warn non-technical users upfront.