We study the problem of making 3D scene reconstructions interactive by asking the following question: can we predict the sounds of human hands interacting with a 3D reconstruction of scene? We focus on human hands since they are versatile in their actions (e.g., tapping, scratching, patting) and very important to simulate human-like avatars in virtual reality applications. To predict the sound of hands, we train a video and hand-conditioned rectified flow model on a novel dataset of 3D-aligned hand-scene interactions with synchronized audio. Evaluation through psychophysical studies shows that our generated sounds are frequently indistinguishable from real sounds, outperforming baselines lacking hand pose or visual scene information. Through quantitative evaluations, we show that the generated sounds accurately convey material properties and actions. We will release our code and dataset to support further development in interactive 3D reconstructions.