MartinDelophy/ai-video-editor

Open-source, local-first video editor where creators and AI agents edit the same real timeline.

What it solves

Timeline Studio is a local-first, browser-based AI video editor that provides professional-grade editing tools (like a multi-track timeline) combined with integrated AI capabilities. It eliminates the need to upload project media to a backend, allowing users to perform complex AI-driven edits, voiceovers, and restorations directly in the browser using WebGPU and WASM.

How it works

The editor uses a CapCut-style multi-track timeline for visual and audio management. It leverages WebGPU and ONNX Runtime to run AI models locally in the browser. Models are lazy-loaded and cached via service workers from mirrors on Hugging Face and ModelScope. For exporting, it uses a deterministic offline rendering path with WebCodecs for MP4/WebM composition.

Who it’s for

Content creators and video editors who want a privacy-focused, local-first AI editing suite that combines traditional timeline editing with AI-powered automation and asset generation.

Highlights

  • Local AI Suite: Includes multilingual TTS (Hojo, Kokoro, Piper), local AI music generation (Stable Audio 3), and automatic captioning (Whisper).
  • AI Video Tools: Features MI-GAN for watermark/object removal, NanoVSR for 4x restoration, and depth-map generation for relighting.
  • Visual Intelligence: YOLOS and MODNet for smart framing, background removal, and subject detection.
  • Digital Human Generation: Audio-to-motion and neural rendering via JoyVASA and LivePortrait.
  • Agentic Editing: Includes a dedicated "AI Video Editing Skill" for LLM agents (Claude Code, Copilot, etc.) to plan and execute edits via a headless command runner or WebMCP integration.

Related

  • Project
    0xsline/OpenChatCut

    An open-source, local-first AI video editor that allows conversational agents to perform editable, multitrack timeline edits rather than just generating immutable videos.

  • Project
    ErickWendel/localstudio

    A browser-native, local-first slide editor that uses Web AI and WebGPU to provide AI-powered slide generation, translation, and presentation tools without a backend.

  • Project
    open-ribbi/velocut

    A browser-based studio that integrates multitrack video editing, 3D scene direction, and AI video generation into a single programmable environment.

  • Project
    jamiepine/voicebox

    An open-source, local-first AI voice studio for voice cloning, text-to-speech, and system-wide dictation, featuring integration with MCP-aware AI agents.

  • Project
    Sportinger/MasterSelects

    A browser-based video editor and extensible workspace that integrates multitrack editing, 3D scene building, and AI-powered tools like SAM 2.1 for video segmentation.