As speech synthesis quality reaches high levels of naturalnessfor isolated utterances, more work is focusing on the synthesisof context-dependent conversational speech. The role of context in conversation is still poorly understood and many contextual factors can affect an utterances’s prosodic realisation.Most studies incorporating context use rich acoustic or textualembeddings of the previous context, then demonstrate improvements in overall naturalness. Such studies are not informativeabout what the context embedding represents, or how it affectsan utterance’s realisation. So instead, we narrow the focus toa single, explicit contextual factor. In the current work, this isturn-taking. We condition a speech synthesis model on whetheran utterance is turn-final. Objective measures and targeted subjective evaluation are used to demonstrate that the model cansynthesise turn-taking cues which are perceived by listeners,with results being speaker-dependent.