This paper explores the effect of prosodic contextual factors for speech synthesis based on hidden Markov model (HMM). In the HMM-based speech synthesis, to model not only the phonetic features but also the prosodic ones, a variety of contextual factors are taken into account in the model training. In a baseline system, a lot of contextual factors are used, and the resultant cost for parameter tying by context clustering becomes relatively high compared to that in the speech recognition. We examine the choice of prosodic contexts by objective measures for English and Japanese speech data which have difference linguistic and prosodic characteristics. Experimental results show that more compact context sets give also comparable or close performance to the conventional full context.