TTS that sounds less fake

[macropoint]

I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at router policy.

[deltastation]

Interesting, I hadn't tried that. That matches what I saw on dual 3090.

[deltagrid]

I don't think that's the whole story. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.

[cobaltspark]

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Phi and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[kernelpeak]

Maybe, but I had the opposite result. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit.