Getting started
Install
- Download EditAI_0.1.0.dmg, open it, and drag EditAI to Applications.
- EditAI is ad-hoc signed and not notarised. The first time, right-click the app and choose Open, then confirm. (Or run
xattr -dr com.apple.quarantine /Applications/EditAI.appin Terminal.)
You need macOS 13 or later. EditAI is tested on Apple silicon.
Import your cameras
Drop one video per camera onto the window (or choose them together). Drop more than once if you like: files collect in a list, and Line up N cameras starts the import. EditAI listens to every camera at once, matches them by their shared sound, builds waveforms and preview stills, and opens the editor as soon as they are lined up. The transcript finishes in the background.
Cameras need to have recorded the same sound, even faintly. Start them within a few minutes of each other.
Choose a model
| Model | Use it when |
|---|---|
| Fast (base.en) | You want the quickest pass. |
| Balanced (small.en) | A good default for clear English speech. |
| Best (large-v3-turbo) | You want the most accurate transcript. |
The model is downloaded once from Hugging Face, only when you ask for it. Models already downloaded by ScreenCraft or OpenClip are reused. You can switch the transcript off; Auto-cut and manual editing do not need it, but Claude does.
Cut it
Ask Claude to edit the project, or press Auto-cut. Then refine by hand and export.
Build from source
Install Rust (stable) and the Xcode command line tools, then build from the repository at github.com/MarshallNickolauson/EditAI. See its README for the steps.