This tool automates the creation of AI-generated YouTube Shorts, targeting content creators looking to quickly produce engaging short-form video content. It leverages multiple AI services to generate scripts, narration, visuals, and captions, significantly reducing manual effort.

How It Works

The pipeline begins with a user-provided text file as source content. This content is fed to ChatGPT for script generation. The script is then narrated using ElevenLabs or OpenAI's text-to-speech. Background images are generated via DALL-E 3. Finally, Captacity, powered by OpenAI Whisper, creates synchronized captions with word highlighting, and these components are assembled into a video file.

Quick Start & Requirements

• Install and run via python main.py source.txt.
• Requires API keys for OpenAI (GPT, Whisper, DALL-E) and ElevenLabs, set as environment variables (OPENAI_API_KEY, ELEVEN_API_KEY).
• Python 3.x environment.
• Custom caption styling can be applied via a settings.json file.

Highlighted Details

• End-to-end AI video generation pipeline.
• Customizable caption styling with word highlighting.
• Utilizes multiple leading AI models for different media types.

Maintenance & Community

No specific information on contributors, community channels, or roadmap is provided in the README.

Licensing & Compatibility

The README does not specify a license. Users should verify licensing for commercial use and compatibility with closed-source projects.

Limitations & Caveats

The tool is heavily reliant on external API keys and associated costs. No information is provided regarding error handling, output formats beyond .avi, or specific hardware requirements beyond a standard Python environment.