I want to build a platform for different groups of people to generate podcast.
They could choose chracter in the show and topic they want them to talk about.
This is definitely possible, and this is definitely already happening. It may be hard for some people to even tell the difference between an AI generated script/audio vs 100% human curated.
I sort of similarly used LLMs and speech synthesis tools to make a prototype that could generate short (<10min) podcasts in Mandarin on any topic I specified. Being interesting is less important in a language learning context, though it's notable that I haven't used the tool much and prefer listening to Mandarin audiobooks and real human podcasts, perhaps because they are more interesting.