Caption Cut runs 100% offline for complete privacy. When you transcribe your very first video, the app will automatically download the Whisper AI models in the background. This first transcription may take a few extra minutes, but all future generations will be instant.
macOS versions with Apple security update support. This is typically the current and two previous versions. Minimum Version 12 (Monterey). Currently optimized for Apple Silicon (M1/M2/M3). Requires 8GB RAM and 4GB free disk space.
Windows 10 (64-bit) or Windows 11. Requires 8GB RAM minimum (16GB recommended for faster AI transcription speeds) and 4GB of free disk space for the Whisper language models.
Windows may show a security warning because Caption Cut is a new app. Click "More Info" → "Run Anyway" to continue safely.