Getting Started

Getting Started / 快速开始

Try the hosted editor / 体验在线版

Open the live editor in a modern Chromium browser. WebGPU is recommended for the heaviest AI features.

使用现代 Chromium 浏览器打开在线编辑器。运行大型 AI 功能时推荐启用 WebGPU。

1. Import an image or video. The first visual is placed on the Visuals track automatically.

2. Add later visuals by dragging them from Media to the Visuals or Overlay lane.

3. Add captions, AI voice, stickers, source audio, voiceover, or music as needed.

4. Preview the composition, then export MP4 or WebM.

5. 导入图片或视频，第一个画面会自动放入 Visuals 轨。

6. 后续画面从媒体库拖入 Visuals 或 Overlay 轨。

7. 按需添加字幕、AI 配音、贴纸、原声、旁白或音乐。

8. 预览合成结果，然后导出 MP4 或 WebM。

Run locally / 本地运行

Requirements: Node.js 20+ and a modern Chromium browser.

git clone https://github.com/MartinDelophy/ai-video-editor.git
cd ai-video-editor
npm install
npm run dev

Run repository checks with:

npm run check

First AI run / 首次运行 AI

The first use of a voice, caption, vision, separation, or digital-human workflow may download model files. Keep the tab open, watch the progress message, and allow the browser cache to complete. Later runs reuse cached assets when possible.

首次使用配音、字幕、视觉分析、人声分离或数字人时，可能需要下载模型。请保持页面打开并关注进度；后续运行会尽可能复用缓存。