mcncarl/jianying-headless

Private source preview: native Jianying drafts, isolated editing/export, and standalone Agent Skill.

What it solves

It provides a way to automate video editing in Jianying Pro (macOS) without manual GUI interaction. It allows users to programmatically generate editable drafts, modify multi-track projects, and export final MP4 files using the local Jianying engine, which is particularly useful for AI-driven video workflows and batch processing.

How it works

The tool acts as a bridge between structured editing plans (JSON files) and the Jianying software. It translates these plans into a format the software can understand to create drafts containing video segments, audio, subtitles, and animations. It includes a Python CLI and an "Agent Skill" interface, allowing it to be integrated into AI agents. The process follows a pipeline: Material and Editing Plan $\rightarrow$ Editable Draft $\rightarrow$ Native Engine Export.

Who it’s for

  • AI developers building automated video production pipelines.
  • Content creators who need to batch-generate video drafts.
  • Developers creating AI agents that can assist in video editing.

Highlights

  • Programmatic Draft Generation: Supports multi-track combinations, speed adjustments, volume, picture-in-picture, and subtitles.
  • Native Export: Uses the local Jianying engine to render H.264/AAC MP4 files.
  • Local Material Import: Handles videos, images (PNG, JPEG, GIF), voiceovers, and music.
  • Agent Integration: Provides a dedicated skill set for AI agents to trigger editing tasks.
  • Non-Destructive Editing: Modifies projects in independent copies to avoid overwriting original drafts.

Related

  • Project
    Tencent-Hunyuan/HunyuanVideo-I2V

    An image-to-video generation framework that transforms static images into high-quality videos using a multimodal LLM for semantic consistency.

  • Project
    Vincentwei1021/anything2explainer

    An AI-driven pipeline that converts topics or documents into narrated motion-graphics explainer videos by using AI agents to write Remotion code.

  • Project
    jd-opensource/JoyAI-Video-Edit

    A real-time, instruction-guided video editing system that uses autoregressive diffusion to edit live video streams or uploads as frames arrive.

  • 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.