In this paper we present a statistical machine translation (SMT) system for Frisian to Dutch and Dutch to Frisian. A parallel training corpus has been established, which has subsequently been used to automatically learn a phrase-based SMT model. The translation system is built around the open-source SMT software Moses. The resulting system, named Oersetter , is released as a website for human end users, as well as a web service for software to interact with. We here discuss the workings, setup and performance of our system, which to our knowledge is the very first Frisian-Dutch SMT system.