@inproceedings{ju2025high-quality,
author = {Ju, Zeqian and Yang, Dongchao and Yu, Jianwei and Shen, Kai and Leng, Yichong and Wang, Zhengtao and Tan, Xu and Zhou, Xinyu and Qin, Tao and Li, Xiangyang},
title = {High-Quality Zero-Shot Podcast Generation},
booktitle = {NeuIPS 2025},
year = {2025},
month = {March},
abstract = {Recent advances in text-to-speech synthesis have achieved notable success in generating high-quality short utterances for individual speakers. However, these systems still face challenges when extending their capabilities to long, multi-speaker, and spontaneous dialogues, typical of real-world scenarios such as podcasts. These limitations arise from two primary challenges: 1) long speech: podcasts typically span several minutes, exceeding the upper limit of most existing work; 2) spontaneity: podcasts are marked by their spontaneous, oral nature, which sharply contrasts with formal, written contexts; existing works often fall short in capturing this spontaneity. In this paper, we propose MoonCast, a solution for high-quality zero-shot podcast generation, aiming to synthesize natural podcast-style speech from text-only sources (e.g., stories, technical reports, news in TXT, PDF, or Web URL formats) using the voices of unseen speakers. To generate long audio, we adopt a long-context language model-based audio modeling approach utilizing large-scale long-context speech data. To enhance spontaneity, we utilize a podcast generation module to generate scripts with spontaneous details, which have been empirically shown to be as crucial as the text-to-speech modeling itself. Experiments demonstrate that MoonCast outperforms baselines, with particularly notable improvements in spontaneity and coherence.},
url = {http://approjects.co.za/?big=en-us/research/publication/high-quality-zero-shot-podcast-generation/},
}