Nowadays the generation of personalized Neuro Musculo Skeletal (NMS) models requires the combination of data from multiple medical imaging modalities and biomedical measurements, an operation that demands the knowledge of many specialized software tools. The aim of the present study is to describe a new application called the NMSBuilder, which provides the user an integrated environment for the generation of NMS models from heterogeneous data towards probabilistic and personalized simulations of the neuromusculoskeletal system. The NMSBuilder is based on a software application framework (Multimod Application Framework, MAF), which is specifically designed to support the rapid development of computer aided medicine applications, integrated with dedicated simulation (OpenSim) and numerical computing (Octave) environments. In this work, we briefly introduce the base framework and we illustrate its use by an example. The subject-specific NMS model of the lower limb was generated from a combination of heterogeneous anatomical data from a cadaver study and the muscle function was simulated using the motion capture from body-matched volunteer. While the NMSBuilder is clearly still a prototype, we believe that it is already capable of being used to solve a number of problems common to many biomedical engineering activities.