These projects demonstrate skills in key areas such as:
Data Gathering, AI integration through APIs (OpenAI) Software development with Python Modular and scalable cloud architecture Automation and optimization of complex workflows Design and implementation of simple graphical interfaces, with plans for future improvement.
*(currently in progress)
LabelTools*
LabelTools is a modular and integrated cloud software designed to meet the needs of music producers and publishers. This all-in-one solution offers various modules that automate and optimize key processes in the music industry: data gathering, audio metadata extraction with complete CSV generation and unique ISRC identifier, release asset creation (press kit, technical sheet, etc.), social media post planning, graphical reports for track appreciation analysis, automatic release folder organization, interview generation, contract management based on metadata, advertising campaign profiling, track performance tracking, and royalty calculations. The software is designed to be expandable with additional modules based on user needs.
VeriText*
VeriText*The “VeriText” project involves developing advanced Python software, integrated with OpenAI APIs, for document retrieval automation and text processing. VeriText will enable the generation of summaries and key points, as well as insert citation coordinates directly into documents, facilitating information control and verification. The software will be distributed on Google Cloud Platform (GCP) to ensure scalability, security, and accessibility for end users. The goal is to make VeriText a marketable SaaS solution for professionals and companies requiring reliable tools for textual content management and verification.
ImageInsight*
ImageInsight*The project involves developing Python software that uses artificial vision capabilities offered by OpenAI APIs for batch image classification and management. The software will analyze images to automatically generate descriptive captions, flag potential issues (such as blur, low resolution, or incorrect orientation), and organize problematic images into dedicated subfolders. Additionally, it will generate a detailed report of operations performed, providing users with a comprehensive overview of the interventions made.
Ideogram Image Generator
Ideogram Image Generator
A sophisticated Python application leveraging Ideogram AI and OpenAI’s GPT-4o to create and manipulate high-quality images through natural language prompts. This intuitive tool combines advanced AI capabilities with a user-friendly interface for seamless image generation workflows.
Key Features:
– Natural language prompt optimization using GPT-4o
– High-fidelity image generation via Ideogram AI
– Interactive prompt refinement system
– Advanced image manipulation (edit, remix, upscale)
– Multi-format export options (PNG, JPEG)
The application features a dual-panel interface with a conversation area for prompt crafting and an image workspace for visualization and editing. Built with Python and CustomTkinter, it integrates OpenAI’s GPT-4 and Ideogram’s API suite, making professional-grade AI image generation accessible through an intuitive interface.
FREE APPS
Here’s some free script to download:
-
YouTube Description Optimizer (click to download the .zip file)
A powerful Python automation tool that seamlessly integrates OpenAI’s language models with YouTube’s API to enhance video descriptions. This script features a user-friendly GUI built with tkinter, enabling content creators to automatically optimize their YouTube video descriptions for better SEO performance. Key functionalities include OAuth2 authentication, batch video processing, and intelligent content enhancement using AI. The tool demonstrates advanced API integration, efficient token handling, and practical application of LLM capabilities in content optimization workflows. Perfect for content creators looking to streamline their YouTube optimization process through AI-powered automation.
HOW TO INSTALL: Use Visual Studio Code and open the folder. Follow the instructions on README.md file to install. Remember to put a .env file with your API keys and a Google OAuth json credentials file in the same folder of the script. Remember to install all required dependencies.
2. Advanced Python Folder Analysis Tool for Video Content (click to download the .zip file)
A sophisticated Python script that provides comprehensive analysis of video-containing folders. This command-line utility automatically calculates total folder size, cumulative video duration, and generates detailed file type summaries. Features include EDL (Edit Decision List) generation in CSV format, video metadata extraction, and automated report creation. The tool demonstrates expert handling of file systems, video processing, and data organization, making it invaluable for video editors and content managers requiring detailed folder insights. Perfect for professionals needing quick, accurate analysis of video project folders.
HOW TO INSTALL: Use Visual Studio Code and open the folder. Follow the instructions on README.md file to install. Remember to install all required dependencies.
3. Video News Aggregator (click to download the .zip file)
An innovative Python application that combines Google’s Vertex AI (Gemini) with YouTube’s API to create a smart content discovery system. This tool automatically searches and analyzes recent YouTube videos based on user queries, providing intelligent summaries and insights. Key features include real-time video filtering (last 48 hours), AI-powered content analysis, and an interactive chat interface for seamless user interaction. The script showcases advanced implementation of AI models and API integration, perfect for content researchers and news aggregators seeking automated, intelligent video content discovery
HOW TO INSTALL: Use Visual Studio Code and open the folder. Follow the instructions on README.md file to install. Put a .env file in the same directory. Remember to install all required dependencies.
