The energy transition faces challenges associated with the integration of variable renewa-ble energy sources, the management of uncertainty, and the increasing complexity of en-ergy systems. In this context, artificial intelligence (AI) has gained a significant role, and more recently, generative AI has begun to be explored as a tool for the analysis and mod-eling of these systems. This study was conducted through a Scoping Review following the PRISMA-ScR guidelines, with the aim of mapping the current state of knowledge regard-ing the use of generative AI in the energy transition. The literature search was carried out in the IEEE Xplore, Scopus, Web of Science, and Springer Nature databases, applying pre-viously defined inclusion and exclusion criteria. Peer-reviewed studies published between 2020 and 2026 were included, forming a final corpus of 12 studies analyzed using a qual-itative and descriptive approach. The results show that generative AI is being applied across multiple areas of the energy transition. Key applications include the generation of alternative energy scenarios, the creation of synthetic data for model training and valida-tion, probabilistic uncertainty analysis, and the design of complex energy configurations in systems with high renewable penetration. Additional contributions involve forecasting and optimizing solar and wind resources, analyzing energy consumption patterns, plan-ning integrated and bioenergy systems, predictive maintenance of solar infrastructure, and improving energy storage and operational resilience in smart grids. Three main ap-plication areas were identified: scenario and data generation, optimization and opera-tional processes, and decision-support for intelligent energy systems. However, limita-tions remain, including limited real-world validation, data dependency, computational scalability challenges, and the lack of regulatory frameworks. The protocol was registered in the Open Science Framework (OSF) under code: 10.17605/OSF.IO/BYM7A.