The present work aims to predict drug release from novel site-specific release isoniazid pellets, in USP dissolution test apparatus 3, using the response surface methodology (RSM). Site-specific release isoniazid pellets were prepared by extrusion-spheronization followed by aqueous coating of Acryl-EZE®. RSM was employed for designing of the experiment, generation of mathematical models and optimization study. A 32 full factorial design was used to study the effect of two factors (at three levels), namely volume of dissolution medium (150, 200, 250 ml) and reciprocation rate (5, 15, 25 dips per min). Amount of drug released in 0.1 N hydrochloric acid at 2 h and in pH 6.8 phosphate buffer at 45 min were selected as responses. Results revealed that both, the volume of medium and reciprocation rate, are significant factors affecting isoniazid release. A second order polynomial equation fitted to the data was used to predict the responses in the optimal region. The optimized conditions resulted in dissolution data that were close to the predicted values. The proposed mathematical model is found to be robust and accurate for optimization of dissolution test conditions for site-specific release isoniazid pellets.