“Why would you go for that opening?! What’s wrong with you?”

Sure, I’ll just sell my car so I can buy a pair of fucking shoes.

“…and a great deal of patience as you wait for each NPC to formulate their replies. In the meantime, they’ll just be standing there looking at you with glassy eyes, smiling.”

Thing is, I really don’t see how that’d work for any useful scenario. Even in this very limited case, natural language processing and response generation is definitely off-loaded to a remote server farm. It certainly isn’t running on the console. TTS for a single characters voice could - but likely isn’t - be done on the hardware, but as I mentioned elsewhere, the voice models for modern text-to-speech synthesis are very, very large. Typically gigabytes of data - per voice. Completely unrealistic for any meaningful game.

Even if all those trained models existed (they don’t - and making one is considerably more work and expense than having a voice actor just deliver a fixed set of lines), I doubt any consumer would be amused by a multi-terabyte download.

Even as it is, the response latency is hilariously bad. I imagine players having to wait seconds for each NPC response would fly as well as a lead brick.

Interesting point, although I don’t see how you’d manage to run modern TTS (the models can get very large, and that’s per voice; as an example Parler-TTS’s mini model is 800Mb, the HQ model is 2.3Gb - for one voice) + a LLM for content synthesis on any personal hardware, console or not. The storage requirements alone would make that grossly infeasible.

Does anybody actually want that, ever?

You… grinds teeth may… have a point.

I have a confession to make: Unless shell script is absolutely required, I just use Python for all my automation needs.