Carnivl.ai
Carnivl.ai is an automated AI-powered content generation platform that revolutionizes social media content creation. The platform leverages advanced AI voice synthesis technology to generate TikTok-style videos featuring over 30 distinct pop culture character voices. Users have the option to automate videos based on certain presets and modifiers using triggers based on new news articles/stock-market updates/crypto updates/etc. Overall, the user has the most control over how their content is automated and produced and can share presets with other users. Note that this project is still under construction and no link is available yet, screenshots and video walkthroughs will be posted below.
4 months
1 Person
Full Stack Developer & AI Integration Lead
Project is under construction
Project is under construction
Project is under construction
30+ Voices
Pop-culture Voice Presets
30+ Styles
AI-Video generation styles featuring script context and visual aid
< 2 min / video
Less than 2 minutes per video generation request
Key Features
Core functionality and capabilities that make this project unique
AI-powered voice synthesis with 30+ character voices
Real-time video generation and processing
User authentication and profile management
Content library and history tracking
Social media optimization tools
Custom voice training capabilities
Batch processing for multiple videos
API access for enterprise users
Technology Stack
Technologies and tools used to build this project
frontend
backend
database
deployment
tools
System Architecture
Microservices architecture with separate services for AI processing, user management, and content delivery. Frontend communicates with Flask API backend, which orchestrates AI model interactions and database operations.
React Frontend
Modern Webapp built with React and TypeScript, featuring responsive design and real-time updates
Flask API Gateway
RESTful API handling authentication, content management, and AI service orchestration
AI Processing Service
Dedicated service for voice synthesis and video generation using multiple AI models
PostgreSQL Database
Primary database for user data, content metadata, and application state
Redis Cache
Caching layer for session management and frequently accessed data
AWS S3 Storage
Scalable media storage for generated videos, audio files, and user uploads
Project Gallery
Visual overview of the project architecture and design
Input
Output
Challenges & Solutions
Key obstacles encountered during development and how they were overcome
Challenges
Integrating multiple AI models for seamless voice synthesis
Optimizing video generation performance for real-time use
Managing large media files and storage efficiently
Creating responsive UI for complex video editing features
Implementing robust user authentication and data security
Solutions
Implemented microservices architecture for scalable AI processing
Used Redis caching for improved response times
Integrated AWS S3 for efficient media storage and CDN delivery
Developed progressive web app features for mobile optimization
Implemented JWT authentication with refresh token strategy