Turning is one of the vital machining processes widely employed in most of the manufacturing industries for removal of excess material from the exterior surface of any of the cylindrical workpieces. In this process, achieving optimal combination of various input parameters is essential for improved product quality, extended tool life and higher machining efficiency. However, optimization of a turning process is truly challenging due to involvement of multiple variables, and complex interactions between the input parameters and responses. Effective optimization should also consider resources, like energy, tools, production time and costs, as they significantly influence environmental impact, process sustainability and profitability. Based on the past data, this paper explores use of five human-inspired metaheuristic algorithms, i.e. teaching learning-based optimization (TLBO), search and rescue optimization (SAR), teamwork optimization algorithm (TOA), human conception optimizer (HCO) and queuing search algorithm (QSA) for optimization of turning of AISI 6061-T6 aluminium. Their performance is assessed based upon quality of the deduced solutions and computational effort. The Pareto optimal front is developed to search out the optimal parametric intermix for the multi-objective optimization problem. Among the considered algorithms, TLBO proves to be most effective in achieving the optimal parameter combination, improving material removal rate, surface roughness and specific cutting energy consumption by 27.08, 36.40 and 31.16% for single-objective optimization; and 15.03, 26.63 and 23.27% for multi-objective optimization, respectively, against the previous study. Values of spacing and hypervolume (two quality measures), and results of Friedman’s mean rank test and Wilcoxon rank-sum test also corroborate its superiority over the other competitors.