This project provides an AI-powered toolkit for generating and distributing short videos, targeting content creators and marketers looking to automate video production and social media posting. It aims to simplify the process of creating engaging video content in bulk, potentially increasing reach and monetization opportunities.

How It Works

The system leverages AI models for video generation, content scripting, and voiceovers. Users can input keywords to generate video scripts, select from various AI voice models (local or cloud-based) for narration, and choose background music. The tool supports batch processing, allowing for the creation of numerous unique videos by mixing and matching video clips, images, and text descriptions. It also includes an automated video uploading feature that simulates user interactions with social media platforms.

Quick Start & Requirements

• Installation: Automated setup scripts (setup.bat for Windows, setup.sh for macOS/Linux) are provided. Manual installation requires pip install -r requirements.txt.
• Prerequisites: Python 3.10+, FFmpeg 6.1.1+, and VC++ redistributable for Windows. For automated uploading, Chrome or Firefox with specific debug configurations is needed. API keys for LLM and cloud voice services (Azure, Alibaba Cloud, Tencent Cloud) are also required.
• Running: Execute streamlit run gui.py or use start.bat/start.sh.
• Resources: Detailed setup guides and video tutorials are available.

Highlighted Details

• Supports local AI models like ChatTTS, Faster-Whisper, and GPT-SoVITS for voice generation and recognition.
• Integrates with major cloud LLMs (OpenAI, Azure, Kimi, Baidu Qianfan, etc.) and cloud voice services.
• Automated video posting to platforms like Douyin, Kuaishou, Xiaohongshu, and WeChat Channels.
• Offers batch video remixing with customizable segment lengths, transitions, and subtitle options.

Maintenance & Community

The project is actively updated, with recent additions including CozyVoice, SenseVoice, Docker support, and a simplified Windows version. Community discussion is encouraged via a WeChat group.

Licensing & Compatibility

The software is licensed under GPL-3.0. Commercial use, redistribution of modified versions, or using the software as part of a commercial product without explicit permission is strictly prohibited. The license explicitly states that commercial use based on this software is not allowed.

Limitations & Caveats

The project's license is restrictive, prohibiting commercial use. Automated posting relies on browser automation (Selenium), which can be brittle and prone to breaking with platform UI changes. Integration with future AI video models like Sora is planned but not yet implemented.