India’s cities are expanding rapidly, and with them grows the need for clean, local, and reliable energy solutions. Urban environments, however, create unpredictable wind conditions due to tall buildings, narrow streets, and constantly shifting airflow. This makes choosing the right wind turbine design a challenge—especially since traditional turbines struggle in such settings. Vertical-Axis Wind Turbines (VAWTs), including Darrieus, Helical, H-Rotor, and Savonius designs, offer promising alternatives because they work well in turbulent, low-space environments. In this work, we introduce a practical decision-making framework that blends real-world geospatial factors with modern data-driven modelling to determine which turbine design best fits each major Indian city. We generated a nationwide dataset using coastal influences, altitude patterns, roughness levels, and seasonal effects, and trained machine-learning models to predict wind speed, power output, and the most suitable turbine type for any location. Our results show that Darrieus turbines perform best in cities with stronger and more consistent winds, while Savonius and H-Rotor designs are better suited for dense urban regions with lower wind speeds. The machine-learning models achieved strong accuracy, making the system reliable for city-wise recommendations. This study provides a simple, adaptable framework that can support rooftop installations, urban planning, and small-scale renewable projects. It brings together engineering understanding and intelligent modelling to help Indian cities harness the winds they experience every day.