Time series have met high interest in various fields for measuring the evolution of a quantity over time. Several machine learning techniques are proposed to extract knowledge from this type of data and make them more meaningful. Clustering is one such prominent technique, for detecting homogeneous subgroups from a data set when there is no prior knowledge about classes. It has been called upon various fields to discover hidden models that arise from the data. In this paper, we propose a new framework called Generative time series Clustering with Bagging (GCBag). It combines the power of several techniques designed for time series. Most existing works use DTW to provide a starting point for HMMs to estimate their parameters. As a result, the estimation becomes dependent on this single provided initialization, which can be biased. The originality of GCBag lies in the use of bagging during the clustering where it significantly raises the stability of models. Consequently, we have succeeded in improving the quality of clustering while preserving the descriptive aspect. Several experiments are conducted to demonstrate the effectiveness of GCBag over the existing models for time series clustering, on both synthetic and real time series data.