StratosHouse/altocue

The AI edit suite for coding agents.
A full open video editing suite your agent drives. It cuts, cleans, grades, captions, animates, adds sound and delivers, and it makes films with no footage at all. Then a separate Editor in Chief has to sign off.
The presenter is AI-generated with Higgsfield. The mistakes are planted. The edit is real.
> Making a launch video? There is a dedicated feature for it, and a skill that runs it from the brief to the finished film. It needs no footage, no filming and no keys:
> bash
> altocue launch my-launch --product "Name"
> Or ask your agent for a launch video. The altocue-launch skill picks it up. See Films with no footage.
## What it does
You hand your coding agent a messy recording, a long talk or just a brief. Altocue gives it the eyes, ears and tools to finish the job.
Reframing that follows. A tall crop that trails someone walking and cuts with the camera, and names the seconds it saw no face. With speaker labels it can also cut to whoever is talking in a wide shot of two, which has not yet worked on real footage. A still crop stays wherever it already works.
Motion tracking. Blur, pixelate, spotlight, a label or a sticker that stays on a face or on a box you draw, followed through the film on your machine.
Cutting. Word-timed transcripts with fillers kept, so cuts land on real speech. Each removal has a reason you can overrule. Or edit the script and get a frame-safe cut.
Sound. Noise and hum out, music under the voice taken off when it is measured and Demucs is installed, each phrase levelled, room tone in the holes, mastered to a measured loudness and true peak.
Colour. HDR to SDR, white balance and exposure read from the face, film looks or your own LUT, with skin protected.
Captions. Word by word, never across a cut, only words really said. Speakers can be named or coloured.
Motion graphics. 151 original formats in 12 groups, timed to speech and placed clear of faces. The Studio collection adds smooth typography, depth, linked handoffs, editing diagrams and endings.
Copyable motion recipes. Every built-in graphic includes an agent prompt, a native example and optional sound notes. Preview the full library and adapt it to your words.
Music and effects. Sound you are allowed to use, with the licence and credit shown before anything downloads. Single CC0 sounds are indexed from open packs by category, from clicks and whooshes to glitches and risers, and paid stores are plain links.
Product UI inserts. Faux product screens built with Stageshow, filmed one fixed frame at a time into an insert that lands on the spoken word, and labelled as a mockup.
Films with no footage. Launch films, explainers, demos, ad cards and more, drawn in code from a storyboard.
Long video to shorts. It finds complete thoughts in your own recordings and cuts each into its own project.
Deliverables. Subtitles, chapters, thumbnails, stems, a version with no music for an app's own song library, and a version for each platform, with the master untouched.
Data checks. It measures the finished film and learns from your own results. It predicts nothing.
The Editor in Chief. It does not mark its own homework. Fact gates in code, then a separate reviewer, then code decides SHIP or FIX.