The field of text-to-speech synthesis and voice conversion is rapidly evolving, driven by the integration of large language models and the development of new techniques such as generative adversarial networks. Researchers are focused on improving the naturalness and quality of synthetic voices, as well as enhancing the customization and adaptability of text-to-speech models. One of the key areas of research is the development of open-source and efficient models that can be easily adapted for various applications, including podcast scenarios and voice conversion. Noteworthy papers in this area include Muyan-TTS, which introduces an open-source trainable text-to-speech model optimized for podcast scenarios, and the Generative Adversarial Network based Voice Conversion survey, which provides a comprehensive analysis of the voice conversion landscape and highlights key techniques and challenges. Additionally, the ClonEval benchmark and the Voice Cloning survey provide valuable resources for evaluating and understanding the state-of-the-art in voice cloning and text-to-speech synthesis.