Data clustering is one of the necessary research fields in data analysis. Clustering is an unsupervised classification method for assigning data objects to separate groups, which are called clusters. So that the similarity of the data within each cluster and the difference between the cluster data is high, a variety of meta-heuristic algorithms can be used to solve this problem. In this paper, a new algorithm created using a combination of African Vulture Optimization Algorithm (AVOA) and Harmony Search (HA) is used. The proposed algorithm is implemented on the clustering dataset of the UCI machine learning repository. Furthermore, the results obtained from the proposed algorithm are compared with other meta-heuristic algorithms. The experiments show that the proposed method has good and better performance than other optimization algorithms.