Troubleshooting

Do I need programming knowledge?

No. The AI agent handles the work. You just explain what you want to make and review whether it looks right.

Does it cost money?

Work handled locally—proxy generation, transcription, editing, and export—is free. Charges apply only when using external APIs, such as cloud transcription or narration generation. Setup and approval are always required before use. Billing never starts silently.

Does it run on Windows?

Yes. Windows, Linux (including WSL2), and macOS are supported. Desktop apps for macOS (Apple Silicon) and Windows (64-bit) are also available on the download page as a Public Beta.

Will the AI overwrite my footage without asking?

No. The design contract says that AI never writes to your original footage in assets/ or inbox/ (→ File map). All edits are recorded in a separate file, edit.json, leaving the originals intact.

Will I lose my work if I stop midway?

No. All progress stays in the project files, so you can pick up where you left off next time. You can also resume from a different entry point, such as switching from the terminal to the app.

How do I update?

Run the installation command again (→ Install). Updates leave your projects and data intact.

It stopped working. What should I do first?

① Read the Japanese instructions in the terminal; they often explain the next step. ② Run the installation command again to get the latest release. ③ If that does not help, ask in one of the places below. A screenshot of the error helps people resolve it faster.

The app looks different from this guide…

The guide may be out of date. Compare each page's “Last updated” information with your app version. The documentation on GitHub is always the current source of truth. Reports of discrepancies are welcome too.