<p>We study Neural Foley, the automatic generation of high-quality sound effects synchronizing with videos, enabling an immersive audio-visual experience. Despite its wide range of applications, existing approaches encounter limitations when it comes to simultaneously synthesizing high-quality and video-aligned (<i>i.e.</i>,semantic relevant and temporal synchronized) sounds. To overcome these limitations, we propose FoleyCrafter, a novel framework that leverages a pre-trained text-to-audio model to ensure high-quality audio generation. FoleyCrafter comprises two key components: a semantic adapter for semantic alignment and a temporal adapter for precise audio-video synchronization. The semantic adapter utilizes parallel cross-attention layers to condition audio generation on video features, producing realistic sound effects that are semantically relevant to the visual content. Meanwhile, the temporal adapter estimates time-varying signals from the videos and subsequently synchronizes audio generation with those estimates, leading to enhanced temporal alignment between audio and video. To further enhance the training of the temporal adapter, we introduce a high-quality audio-video synchronized dataset with strong, clear visual cues closely tied to their corresponding audio sounds, TikTokSound. We conduct extensive quantitative and qualitative experiments on standard benchmarks to verify the effectiveness of FoleyCrafter. Models and codes will be available.</p>