Hi, I'm Rubel Amin
AI Video Generation Platform Developer
Full-Stack Engineer specializing in Next.js and AI Video Systems. I build cutting-edge Text-to-Video, Image-to-Video, and Speech-to-Video pipelines that transform ideas into visual stories.
Skills & Tech Stack
Technologies I use to build scalable AI-powered applications and video generation systems.
Expertise & Experience
Specialized capabilities in AI video generation and full-stack development.
AI Video Generation Pipelines
Building end-to-end video generation systems that transform text, images, and speech into professional-quality videos using cutting-edge AI models.
API-Based AI Integrations
Expert integration of AI APIs including OpenAI, Stability AI, ElevenLabs, and custom model endpoints for seamless AI-powered features.
FFmpeg Video Processing
Advanced video processing workflows using FFmpeg for encoding, transcoding, concatenation, and real-time video manipulation at scale.
Queue Systems & Background Jobs
Implementing robust job queue systems using BullMQ and Redis for handling long-running video processing tasks efficiently.
Scalable Backend Architecture
Designing and building scalable Node.js backends with microservices architecture, load balancing, and horizontal scaling capabilities.
Cloud & DevOps
Production deployments using Docker containers, CI/CD pipelines with GitHub Actions, and VPS management for cost-effective hosting.
Featured Projects
AI-powered video generation systems built with modern technologies.
AI Video Generator Platform
A comprehensive Text → Scene → Image → Voice → Video pipeline that transforms written scripts into fully produced videos with AI-generated visuals and voiceovers.
Key Features
- Text-to-Scene parsing with AI
- AI Image generation per scene
- Text-to-Speech voiceover synthesis
- Automated video compilation
Image-to-Video System
Transform static images into dynamic videos with smooth transitions, Ken Burns effects, and synchronized audio narration.
Key Features
- Multi-image story creation
- Smooth transition effects
- AI-powered narration sync
- Custom duration control
Speech-to-Video Generator
Convert audio recordings or synthesized speech into engaging videos with real-time visual generation matching the spoken content.
Key Features
- Speech-to-text transcription
- Context-aware scene generation
- Real-time video preview
- Export in multiple formats
Get In Touch
Have a project in mind? Let's discuss how I can help you build cutting-edge AI video solutions.
Or reach out directly
contact@rubelamin.com