AuraAI is an end-to-end Generative AI application that transforms a simple text prompt into a narrated video with AI-generated visuals, voice narration, and subtitles.
The application leverages multiple AI services to automate the complete content creation pipeline, making it possible to generate engaging short stories and videos with minimal user input.
- Generate creative stories from user prompts using Google Gemini API
- Generate AI images for each scene using Stability AI
- Convert story narration into realistic speech using ElevenLabs API
- Automatically generate videos using MoviePy
- Generate and overlay subtitles on the final video
- End-to-end automated AI workflow
User Prompt
│
▼
Gemini API
(Story Generation)
│
▼
Scene Extraction
│
▼
Stability AI
(Image Generation)
│
▼
ElevenLabs
(Voice Generation)
│
▼
MoviePy
(Video + Audio + Subtitles)
│
▼
Final AI Generated Video
- Python
- Google Gemini API
- Stability AI API
- ElevenLabs API
- MoviePy
- Requests
- Pillow
- Python-dotenv
- Designed an end-to-end LLM-powered content generation pipeline
- Integrated multiple AI APIs into a single automated workflow
- Generated scene-wise AI images based on story context
- Automated voice narration using realistic AI speech synthesis
- Created videos programmatically with synchronized audio and subtitles
- Developed a modular and extensible architecture for AI content generation
git clone https://github.com/swet40/AuraAI.git
cd AuraAI
pip install -r requirements.txtCreate a .env file and add:
GEMINI_API_KEY=YOUR_KEY
STABILITY_API_KEY=YOUR_KEY
ELEVENLABS_API_KEY=YOUR_KEY