Norsico/Video-Materials-AutoGEN-Workstation

一个集内容策划、AI文案自动生成、TTS 批量自动配音、(AI)图片素材合成、ASR自动提取语言字幕脚本、AI自由创作于一体的(短视频)生成工作站。方便管理每期的视频项目。

What it solves

This project provides a centralized workstation for short-video creators to manage the production pipeline. It automates the generation of scripts, AI voiceovers, image assets, and subtitles, reducing the manual effort required to coordinate multiple AI tools for a single video project.

How it works

The workstation acts as a management layer that integrates several AI capabilities via APIs. It uses Gemini for script rewriting and text generation, TTS (Text-to-Speech) engines for emotional voiceovers, and image generation models (such as NanoBanana via AIStudio reverse proxy) for visual assets. It also includes tools for ASR (Automatic Speech Recognition) to extract subtitles from existing videos.

Who it’s for

Content creators and short-video producers who want to streamline their workflow by managing scripts, audio, and images in one place using AI automation.

Highlights

  • Integrated Pipeline: Combines content planning, script generation, TTS voiceovers, and image synthesis in one interface.
  • Batch Processing: Supports creating multiple video projects from templates with one-click generation of scripts, images, and audio.
  • Asset Management: Features a track-based management system for images, subtitles, and audio, allowing for easy replacement and previewing.
  • Multi-modal AI Integration: Leverages Gemini for text, various TTS for audio, and specialized image models for visual content.

Related

  • Project
    guochengqian/Magic123

    A system for generating high-quality 3D objects from a single 2D image by combining 2D and 3D diffusion priors in a coarse-to-fine pipeline.

  • Project
    shrimbly/node-banana

    Node Banana is a macOS‑first visual editor that lets users build, run, and share AI media pipelines (image, video, audio, 3D, text) by connecting typed nodes on a canvas. It supports multiple providers, offers dynamic prompting, an LLM‑driven “agent” chat, and stores all keys and assets locally.

  • Project
    modelcontextprotocol/php-sdk

    MCP PHP SDK is a framework‑agnostic library for building Model Context Protocol servers and clients in PHP. It provides attribute‑based tool/resource definitions, STDIO/HTTP transports, client helpers, and weekly conformance testing, enabling PHP applications to expose AI‑callable functions to LLMs.

  • Project
    om-ai-lab/VLX-Seek

    VLX-Seek is a fine-grained perception VLM that replaces coordinate generation with region-token retrieval for more stable and efficient object localization in embodied AI.