Music captioning has gained significant attention in the wake of the rising prominence of streaming media platforms. Traditional approaches often prioritize either the audio or lyrics aspect of the music, leading to suboptimal results. By leveraging alignment-augmented models, we can better capture the intricate relationships between audio and lyrics, resulting in more accurate and informative captions. This research activity aims to explore the potential of alignment-augmented models in music captioning, with a focus on improving the overall quality and coherence of generated captions.