Transcript-first selection
Word-timed transcripts (local ASR with provenance) anchor every boundary to a real sentence. Proposals without transcript evidence are rejected, not guessed.
Local-first · Offline · Human publishes
ClipFactory is a local batch clipper for vertical video: transcript-first candidate selection, multi-beat FFmpeg rendering, deterministic QA gates, and Editing DNA style transfer from a reference video. No uploads, no auto-posting, no surprises.
real clip record
clip_id candidate-061 range 174.6s – 184.0s render 8.5s · 720x1280 verdict review_required qa PASS · gemmy captions
Safety promise: ClipFactory never joins a campaign, posts, submits, spends money, or mutates an account. Everything stops at local render — publishing is a human act.
What it does
Word-timed transcripts (local ASR with provenance) anchor every boundary to a real sentence. Proposals without transcript evidence are rejected, not guessed.
Clips render as structured beats — hook, body, payoff — reframed to 9:16 with captions overlaid exclusively by Gemmy Caption. Replaceable fills let you swap a beat without re-rendering the world.
Every render passes media checks (black frames, freezes, silence, A/V drift), caption QA, and visual QA. Outcomes are typed: publish-ready, review-required, or blocked — with reasons attached. The gates bite, including on our own showcase below.
Point at a reference video you admire. ClipFactory extracts its editorial behaviors, plans an edit of your raw footage in that style, validates the plan, then renders.
One caption renderer, no fallbacks: HyperFrames rails (highlight, pill-karaoke, gradient-fill, editorial-emphasis, weight-shift…) overlaid by Gemmy. If Gemmy is missing, the render fails loudly instead of degrading silently.
Ships as a foundry-plugin.v1 capability pack: 8 commands (batch select/render/run, DNA extract/plan/render/assemble/variant) with schemas and typed results.
How it works
Track A · Batch clipping
Track B · Editing DNA
Ranking rule the engine enforces: QA status and evidence rank clips. Predicted views are never a ranking input.
Real outputs · rendered by the engine
Everything below is genuine ClipFactory output, rendered on a local machine from a 27-minute 4K source (GTA VI Trailer 2, extended look — rights practice-only, excerpts shown to demonstrate the tool). Transcript: 2,623 words / 243 segments, provider gemmy-parakeet. Captions: Gemmy Caption exclusively. QA verdicts included unedited — including the failures.
Transcript-first selection picked 2 non-overlapping candidates from the full source. Both rendered 720×1280/30fps, both QA PASS, both review_required — the engine does not auto-approve.
174.6s – 184.0s → 8.5s render · highlight rail
“My partner's off the grid right now, you feel me?”
media QA pass caption QA pass review_required
36.2s – 51.8s → 5.4s render · highlight rail
“Yeah, go inside and ask for Raymond, bro”
media QA pass caption QA: 1 short cue review_required
Controlled variant: same 8.5s moment, only the caption rail changes (control highlight, challengers pill-karaoke / weight-shift / gradient-fill / editorial-emphasis). Two rails failed the A/V drift gate — Gemmy's karaoke and weight-shift overlays truncate ~3 frames, deterministically, twice in a row. The gate caught it; the clips stay review_required.
QA pass
drift 0.090s > 0.08 gate
drift 0.090s > 0.08 gate
QA pass
QA pass
Reference: 60s slice → 12-shot event graph → interpretation (pacing, cut policy, caption policy, structure supported; zoom, b-roll unresolved). Planner grok-4.6 via local OAuth bridge: first draft rejected by the validator, repair pass accepted. The plan declines what the evidence can't support — zoom holds only, no b-roll, 4 rejected alternatives, 3 stated uncertainties. Target canvas preserved by design (DNA keeps source aspect; 9:16 is the batch track's job).
29.2s · captions auto/middle · validator: accept after 1 repair
plan accept uncertainties admitted: 3
How this page was made
All artifacts (candidate bank, edit plans, QA reports, planner I/O) live with the run; videos: showcase-v1 release.
Editing DNA
Analyze a reference video into a reusable style — pacing, caption behavior, inserts, reframes — then apply it to your own raw footage. Three styles ship as examples (see one working above):
python -m clipper_engine.cli style-analyze --source reference.mp4 --name MyStyle python -m clipper_engine.cli style-list python -m clipper_engine.cli edit-generate --style STYLE_ID --target raw.mp4 --out ./edit
Quickstart
Prerequisites
Install & run
pip install -e . python -m clipper_engine.cli batch-run --help python -m clipper_engine.cli app # desktop app, no quotas python -m editing_dna --help # style-transfer track
The engine source is in private beta — request access and the same commands work after checkout.
Platform
ClipFactory ships as a foundry-plugin.v1 capability pack. Eight typed commands, JSON schemas for every input and output, structured events and results — spawned exactly like the host runs them and covered by a conformance suite.
| Command | Does |
|---|---|
| clip.batch-select | Transcript-first candidate bank across a batch |
| clip.batch-render | Render + QA the selected candidates |
| clip.batch-run | Select, render, and QA end to end |
| dna.extract | Reference video → validated event graph |
| dna.plan | Planner input → validated edit plan |
| dna.render | Accepted plan + sources → styled video |
| dna.assemble | Replaceable beat-list assembly |
| dna.variant | Swap one beat, keep the body |
Safety
FAQ
No. It renders video files and evidence on your machine and stops. Uploading, posting, and submitting are human acts it cannot perform.
No. Selection, rendering, and QA run locally with FFmpeg, Gemmy (local GPU), and deterministic validators. The DNA planner can point at any OpenAI-compatible local lane; the showcase transfer above was planned by Grok through a local OAuth bridge — still no provider keys in the repo.
Yes. Real engine outputs from a 27-minute source, with real transcripts, real caption rails, and real QA verdicts — failures included. Videos stream from public release assets; this page itself is static and collects nothing.
Clips rank by QA status and evidenced score. Predicted views are never a ranking input, and financial summaries never treat raw views as cash.
The engine is in private beta while the platform matures. Request access here — this page and its evidence are public and open.
Watch the outputs, then request access to the engine when you're ready.