Most of modern machining are characterized by high spindle speeds and increased cutting forces. All of this results in increased wear for cutting tools and ultimately has its impact on the surface quality of the product. Extreme temperatures and operating conditions at the cutting edge render it difficult for measurement of real-time tool wear monitoring. Since tool wear is a direct indicator of surface quality of the product, the vibration signatures of single point cutting tool during are important indicators of surface quality. The current study focuses on employing such vibration signatures of an EDM textured single point cutting tool and an ANN model for predicting the surface roughness during turning of EN-9 steel material. The experimentation data is used to train the model for different machining settings and further a prediction model using multi regression and ANN is developed which combines the input machining condition data along with tool vibrations. Such study can be useful in exploring the effects of tool rake face texturing on the surface roughness and tool vibration.