jub0t/Concat

Free & Open-Source CapCut replacement.

What it solves

Concat is a free, open-source alternative to CapCut, providing a professional video editing suite that operates entirely locally. It removes the need for subscriptions, accounts, watermarks, and cloud-based processing, ensuring user privacy and accessibility across macOS, Windows, and Linux.

How it works

The application combines a native Rust engine for high-performance processing with a React-based user interface for the editing experience. It integrates tools like Whisper for local auto-captions and ffmpeg for video manipulation, allowing all editing and AI-powered features to run on the user's own hardware.

Who it’s for

Content creators and video editors who want a powerful, local-first video editing tool without the paywalls or privacy concerns associated with proprietary software.

Highlights

  • Local AI Features: Includes free, local Text-to-Speech and auto-captions that process audio without sending data to the cloud.
  • Multi-track Editing: Supports multiple timelines per project for complex edits.
  • Comprehensive Toolkit: Offers standard editing tools including splitting, trimming, merging, transitions, and speed control.
  • Audio Tools: Features voice filters for sound cleanup and manipulation.
  • Reusable Templates: Allows users to build an edit once and reuse it for future videos.
  • Cross-Platform: Native support for Windows, macOS, and Linux.

Related

  • Project
    Agents365-ai/video-podcast-maker

    An automated pipeline that transforms a topic into a professional 4K video podcast by integrating AI research, TTS audio, and Remotion-based video rendering.

  • Project
    AIMixer/ComfyUI_MiniMaxH3_Director

    A ComfyUI plugin that provides a UI‑driven “director” node for multi‑segment video generation with MiniMax‑H3 models, supporting text, image, reference, and video‑to‑video tasks, audio generation, motion continuity, second‑pass refinement, and import/export of project packs.

  • Project
    Robbyant/lingbot-world-v2

    LingBot‑World‑V2 is a research‑grade video‑generation model that creates infinite, interactive worlds from text prompts. It offers fast (real‑time) and high‑quality variants (14 B and 1.3 B), supports diverse actions, and uses a pilot‑director agent architecture. The repo provides inference code, model download links, and a quick‑start guide; deployment code is not released.

  • Project
    Vchitect/VBench

    VBench is an open‑source benchmark suite that automatically evaluates video‑generation models across dozens of quality dimensions (technical, aesthetic, and trustworthiness). It includes prompt collections, metric pipelines, human‑aligned scores, and public leaderboards for T2V, I2V, long‑video, and intrinsic‑faithfulness evaluation.