This project automates YouTube video creation from text prompts, targeting YouTube creators and automation enthusiasts. It leverages AI for script generation, voiceovers, and video compilation, aiming to streamline content production and enable rapid channel growth.

How It Works

The system generates video scripts and associated search queries for stock footage using OpenAI's GPT-3. It then synthesizes natural-sounding voiceovers with the Bark text-to-speech model. Video clips are sourced from YouTube or Storyblocks based on generated queries. While basic video stitching is implemented with MoviePy, the current workflow relies on manual compilation in Adobe Premiere Pro for speed.

Quick Start & Requirements

• Install dependencies: pip install -r requirements.txt and pip install git+https://github.com/suno-ai/bark.git.
• Requires cookies.json for Storyblocks access and env.yaml with OpenAI API key and working directories.
• Input prompts and content must be placed in the prompts and SOURCE_DIR respectively.
• Run app.py to start the process.
• Dependencies include OpenAI GPT-3 API, Bark TTS, Python Requests, and MoviePy.

Highlighted Details

• Achieved ~8,000 views and 70 subscribers in ~25 days on a finance-focused YouTube channel with daily uploads.
• Utilizes Bark for high-quality, natural-sounding voice generation.
• Script generation includes queries for sourcing video clips from YouTube/Storyblocks.
• Current video compilation is a manual step in Adobe Premiere Pro due to MoviePy's slow performance.

Maintenance & Community

• Primary contributor: Art Kulakov.
• No explicit community links (Discord/Slack) or roadmap are provided in the README.

Licensing & Compatibility

• Licensed under the MIT License.
• Permissive for commercial use and integration with closed-source projects.

Limitations & Caveats

The video compilation process is currently manual and relies on external software (Adobe Premiere Pro) due to the slow performance of the included MoviePy implementation. Enhancements for high-quality text overlays and image-based parallax effects are noted as areas for future improvement.