Existing Existing automatic audio generation methods struggle to generate podcast-like audio programs effectively. The key challenges lie in in-depth content generation, appropriate and expressive voice production. This paper proposed PodAgent, a comprehensive framework for creating audio programs. PodAgent 1) generates informative topic-discussion content by designing a Host-Guest-Writer multi-agent collaboration system, 2) builds a voice pool for suitable voice-role matching and 3) utilizes LLM-enhanced speech synthesis method to generate expressive conversational speech. Given the absence of standardized evaluation criteria for podcast-like audio generation, we developed comprehensive assessment guidelines to effectively evaluate the model's performance. Experimental results demonstrate PodAgent's effectiveness, significantly surpassing direct GPT-4 generation in topic-discussion dialogue content, achieving an 87.4% voice-matching accuracy, and producing more expressive speech through LLM-guided synthesis. Demo page: https://podcast-agent.github.io/demo/. Source code: https://github.com/yujxx/PodAgent.

In this article I'll show you a case study describing an entire process of designing a conversational UI for a B2B website, including fragments of the conversation script, basics of the communication theory and some of the tips and tricks I think make this project a bit unique. Many people say conversational UI is the future of web interface. Some might say it's just another design fad or that text-based interfaces aren't anything new, but frankly -- let's admit it -- with the advent of iPhone Messages, Slack or Facebook Messenger the way we exchange information changed irreversibly. Text messages have became extremely natural way of communicating these days. So naturally, when a chance arose for The Rectangles to work on a conversational website for one of our clients, we didn't hesitate a single second.