SuperAPI AI Directory

Wunjo

Wunjo is an open-source multimedia creation and editing software that supports the processing and generation of video, images, and audio. Its main features include face swapping, real-time portrait and facial reenactment, video generation, lip sync, object and background removal, style repainting, voice cloning, and more. Users can use it for free locally or via API calls. The product offers two versions: Wunjo Community Edition (CE) and Wunjo Professional (Pro). The suite integrates the complete workflow from source file preparation to scriptwriting and video editing, comes with the Wunjo Design vector editor and Wunjo Make video editor, and supports connecting intelligent agents (local or Cursor, Claude Code, Codex, etc.) as well as plugin extensions, making it suitable for creators, freelancers, and teams for integrated media content production.

Open website

About this tool

Wunjo is an open-source software for the creation and processing of video, images, and audio. According to official information, its features cover face swapping, real-time portrait and facial reenactment, video generation, lip sync, object and background removal, style repainting, voice cloning, and more, and it can be used for content production. The software offers two ways to use it: run it locally for free, or call it via API; in terms of versions, you can choose Wunjo Community Edition (CE) or Wunjo Professional (Pro).

In terms of purpose, Wunjo is positioned as an all-in-one media suite covering the complete path of content production, aimed at creators, freelancers, and teams. It officially describes the production of any clip and graphic as divided into two stages: preparing source files, and scriptwriting and video editing.

Main capabilities include:

  • Source file preparation stage: use the free vector editor Wunjo Design, operating directly in the browser. Users can draw characters, details, and spaces themselves or with the help of neural networks; schematically draw the movement paths of characters or cameras in different colors to distinguish movement routes. After the first load, most functions of the service can run offline.
  • Scriptwriting and video editing stage: use the video editor Wunjo Make installed on the computer. Intelligent agents can be connected (local agents or Cursor, Claude Code, Codex), and plugins can be installed from the plugin library to extend the editor. After attaching source files in the chat, the agent can use them to write scripts, plan steps, and generate and edit video and sound (locally or through services). It can find suitable files on the computer by itself and integrate them into the final cut. Users can describe ideas through prompts and combine them with ready-made skills and scripts.
  • Other specific features: create scenes with synchronized sound from text, images, and clips; create media based on photos, reference styles, and clips; facial expression changes, emotion control, and head rotation; lip sync in photos or videos to match audio dubbing; voice cloning and noise reduction; local agents for editing and MCP control; and dozens of tools as officially claimed.

In terms of usage, two paths are officially provided: first, directly use ready-made files or reproduce the examples yourself—the room sketch (including characters and camera paths) can be opened in Wunjo Design, modified, and exported as PNG; the generated clips and edited project are packaged in a compressed file, and after extraction, open the .wmproj file in Wunjo Make to see how the agent builds the timeline. Second, do it yourself: first install Wunjo Make, then install plugins, attach from Wunjo Design in the chat Export the image and paste the prompt (for example, describe a person wearing a white hoodie walking along a red path through a room, the camera following along a blue path, warm evening light, handheld feel, 8 seconds), or connect to a cloud agent via MCP, or install the Qwen 3.5 plugin for offline editing, then paste the prompt; finally take the clips from the project folder, cut them into 20-second segments in path order, match cuts on motion, add ambient room sound and a soft beat, and export in 9:16 and 16:9 formats.

Regarding use cases, the official list of commercial use cases includes: marketing, sales, ad creatives, and A/B testing; turning photos of old items or new products into videos for product listings and marketplace platforms; creating game cutscenes and promoting games on social media; creating clips on any topic for audiences of any age; and generating engaging videos for listings and bookings from photos of an apartment or room, without the need for expensive professional shoots.

Regarding limitations, the official materials do not clearly state specific pricing, system requirements, platform compatibility, or other usage restrictions; this information is not currently provided.