Don't be shy generated using VITS (Kim, Jaehyeon, Jungil Kong, and Juhee Son. "Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech." arXiv preprint arXiv:2106.06103 (2021). ) (custom trained)
http://www.nicovideo.jp/watch/sm41912341