There are 3 repositories under expressive-tts topic.
PyTorch Implementation of Non-autoregressive Expressive (emotional, conversational) TTS based on FastSpeech2, supporting English, Korean, and your own languages.
Official repository of STYLER: Style Factor Modeling with Rapidity and Robustness via Speech Decomposition for Expressive and Controllable Neural Text to Speech, INTERSPEECH 2021
PyTorch Implementation of Robust and fine-grained prosody control of end-to-end speech synthesis