This repository aggregates academic papers and implementations across speech and audio generation domains including text-to-speech, singing voice synthesis, voice conversion, and music synthesis. It covers work from top conferences (NeurIPS, ICML, INTERSPEECH, ICASSP) and journals, featuring systems built with diffusion probabilistic models, self-supervised learning, and neural vocoders. The list serves as a reference for researchers and developers working on generative audio and speech synthesis.