Chat2Editing

AI-Powered Video Editing Assistant for macOS

Version 1.0

Getting Started

1. Import your clips — Drag and drop or use ⌘I to import video/audio files (MOV, MP4, MXF, WAV, MP3, and more).
2. Transcribe — Click the Transcribe button. On first use, speech recognition models will be downloaded automatically (one-time only).
3. Chat & Search — Use the chat panel to ask questions about your clips in plain language, e.g. "Find all scenes about the budget."
4. Export — Export selected segments as FCP XML or EDL to import directly into Final Cut Pro, DaVinci Resolve, Premiere Pro, or any NLE.

System Requirements

• macOS 26 (Tahoe) or later
• Apple Silicon Mac (M1 or later)
• Apple Intelligence enabled
• Internet connection for first-time model download only

FAQ

Why is the first transcription slow?

On first use, Chat2Editing downloads speech recognition models (40 MB – 1.5 GB depending on the model you choose in Settings). After this one-time download, transcription works offline and is much faster.

Does Chat2Editing send my data to the cloud?

No. All processing — transcription, speaker identification, and AI chat — happens entirely on your Mac. See our Privacy Policy for details.

Which model size should I choose?

For most users, Base (~80 MB) or Small (~250 MB) offers a good balance of speed and accuracy. For professional use with complex audio, try Large (~1.5 GB). You can change the model anytime in Settings.

What export formats are supported?

FCP XML (for Final Cut Pro) and EDL/CMX 3600 (for DaVinci Resolve, Premiere Pro, and other NLEs).

Can I search across multiple clips?

Yes. Select multiple clips in the sidebar, then use the chat to search across all of them at once.