Turn a written script into a fully edited video with voiceover, subtitles, and cover images.
Use AI review to improve and revise a video script before recording.
Import existing audio and subtitles and build a video timeline around them.
Control the video editing workspace programmatically using Claude Code or another MCP compatible AI agent.
| yoqu/lingji-cut | 5bv57zcm44-max/noxus-ai-open-whatsapp | adrianhajdin/react-native-lingua | |
|---|---|---|---|
| Stars | 27 | 27 | 27 |
| Language | TypeScript | TypeScript | TypeScript |
| Setup difficulty | moderate | moderate | moderate |
| Complexity | 3/5 | 4/5 | 3/5 |
| Audience | vibe coder | developer | vibe coder |
Figures from each repo's GitHub metadata at analysis time.
Requires npm install and connecting your own AI, image, and text to speech provider API keys through the app's settings.
Lingji Cut, also written as Ling Jian, is an open source desktop first AI video creation workspace. It brings together the scattered steps of content production, writing a script, managing raw materials, generating voiceover, creating subtitles, assembling a timeline, and exporting the final video, into one application that runs on your own computer. The typical workflow starts with a script. You write or import your source text, and the app's AI scriptwriting workspace helps you draft, revise, and review it, including an AI review mode that annotates and suggests improvements. From the script you can trigger an automated pipeline: the app generates a text to speech audio track, parses subtitles, analyzes the content to pick cover images and visual cards, and arranges everything on a video timeline. You then adjust timing, clips, subtitles, and graphics in a multi track timeline editor before exporting an MP4 file. The app connects to several external AI services for different tasks: large language models for writing help, supporting OpenAI compatible providers and Gemini, plus separate image generation services and a text to speech service for voiceover. It also connects to the Claude AI agent runtime and exposes MCP tools, a standard that lets AI agents interact with applications, so tools like Claude Code can script and control the workspace directly. Project files, including the script, audio, subtitles, and configuration, are saved to a local folder the user chooses, and the README states that no real API keys are stored in the repository itself. The project is built with Electron for the desktop shell, React and TypeScript for the interface, and Remotion for programmatic video rendering. It currently targets macOS and Windows desktops and is released under the Apache License 2.0.
A desktop app that turns a script into a finished narrated video using AI writing help, text to speech, subtitles, and automatic timeline editing.
Mainly TypeScript. The stack also includes Electron, React, TypeScript.
Use freely for any purpose, including commercial use, as long as you keep the copyright and license notice.
Setup difficulty is rated moderate, with roughly 30min to a first successful run.
Mainly vibe coder.
This repo across BitVibe Labs
Verify against the repo before relying on details.