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.

I made a prototype, I told 2 host to explain one book acutally it works really well after using in-context learning except for sounds.