Face age synthesis aims to alter an individual's face to predict the facial image's future or past appearance. Face age synthesis has applications in many areas, including law enforcement and tracking victims of human trafficking. This work uses conditional variational autoencoder generative adversarial networks. The encoder network converts a facial image into a latent representation. The decoder network is used to generate images of the desired age by using this latent representation. The Discriminator network is used to check the authenticity of the image. The proposed system is evaluated on a publicly available Cross-Age Celebrity Dataset. This chapter focuses on facial images from people in their late teens to older adults. Different tests are conducted to measure and analyze the outcomes. Experimental results obtained using metrics such as age estimation error, cosine similarity, and identity preservation show the feasibility of the framework. The proposed solution provides a viable methodology for solving the problem of face-age synthesis.