Explainer
A small desk reset. Original illustrations, thirteen beats and a useful takeaway.
Start from a complete project, make one visible change, and render on your computer. Keep the source so you can change it again.
The supplied examples already include narration and word timings. Your first export needs the local tools below; an AI account and optional speech models can wait.
Open the extracted local-video-kit folder in a terminal. Install Node.js 20.9 or later, FFmpeg with libx264, FFprobe and Python 3.10 or later using the setup guide. Then run:
npm ci
node scripts/first-video.cjs doctorFix a failed check before continuing. Initial installation requires internet. Supplied audio needs no model download; new local speech has its own optional setup.
This page is a read-only guide. Copy commands into your terminal; the buttons do not run a render. The complete model route is tested on Apple Silicon macOS. Other systems remain unverified.
Choose a starter and a new output folder. This example uses the explainer with the dark Night Studio profile. Leave out --profile for Field Notes. Your supplied starter stays intact.
node scripts/first-video.cjs init --starter explainer --profile profiles/night-studio.json --out projects/my-first-video
node scripts/first-video.cjs status projects/my-first-videoFor another project, use product-demo or recording-edit as the starter name and choose a new folder. Existing project folders are protected.
Give the opening a shorter headline. This command updates both format plans and validates text fit.
node scripts/first-video.cjs edit projects/my-first-video --headline "Make space for your next idea."This edits the visual title. Narration and caption words stay intact. A new spoken story needs a new script, permitted audio, alignment and retiming. The editable plans, words, sound plan and rights record are in your project folder.
Build both native layouts and wait for the command to finish. Then watch both MP4s all the way through with sound.
node scripts/first-video.cjs render projects/my-first-video --format bothprojects/my-first-video/outputs/ landscape.mp4 · 1920 × 1080 portrait.mp4 · 1080 × 1920 landscape.srt + landscape.vtt portrait.srt + portrait.vtt first-video-build.json
Check captions, text size, crops, speech continuity, scene changes and the final frame. After intentionally editing this working copy, use --force to replace its exports. Render timing depends on your computer.
Choose a fresh delivery folder outside your working source. The helper decodes the video, checks caption structure and declared rights, and verifies hashes after copying.
node scripts/first-video.cjs deliver projects/my-first-video --format both --out deliveries/my-first-videoEach format gets the movie, English SRT/VTT, a cover, editable source, rights records and a checksum manifest. Unresolved rights stop delivery. This does not publish or upload anything.
These players show actual supplied horizontal exports. The download also includes native vertical movies, editable plans, final narration, timings, sound cues and rights records for each.
A small desk reset. Original illustrations, thirteen beats and a useful takeaway.
A fictional task app. Replace its name, screens and story with your own.
Original animated practice footage. Your own recording needs matching words, timing and permission.
Ask your local coding assistant for a specific change in plain English, then validate and render again. Profiles cover supported settings; they preserve spoken words and image pixels. Human presenter generation is not included for free.