dataants-ai/cutscript

CutScript is an open-source desktop app that lets you edit audio and video by editing text. Instead of scrubbing through a timeline, you see a full transcript of your recording. To cut something out, you simply delete the words from the transcript, and the corresponding audio or video is removed automatically. Think of it like editing a document, except the result is a trimmed video file. When you import a video, CutScript uses WhisperX, an AI transcription tool, to generate a word-level transcript, meaning each word is precisely aligned to the moment it appears in the video. From there, you can delete filler words, rearrange clips, or use AI features to automatically remove ums and ahs or generate short-form clip suggestions for platforms like YouTube Shorts. The app can export your final video up to 4K resolution using FFmpeg, a widely used media processing tool. You would use CutScript if you regularly record podcasts, screen recordings, or video tutorials and want a faster way to edit without learning traditional timeline-based video editors. The tech stack includes Electron and React for the desktop interface, a FastAPI Python backend that runs locally in the background, WhisperX for transcription, FFmpeg for video processing, and optional AI integrations with Ollama, OpenAI, or Claude for smart editing features. It runs entirely on your own machine with no cloud dependency required.