We propose a stochastic model for epidemic spreading of the novel coronavirus based in data supported by the Brazilian health agencies. Furthermore, we performed an analysis using the Fokker-Planck equation estimating the novel cases in the day t as the mean half-width of the distribution of novel cases P(N,t). Our results display that the model based in the Itô diffusion adjusts well to the results supplied by health Brazilian agencies due to large uncertain in the official data and to the low number of tests realized in the population.