+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Generative AI (https://www.datasculpting.ai/inference/forumdisplay.php?fid=17)
+--- Forum: Image (https://www.datasculpting.ai/inference/forumdisplay.php?fid=69)
+--- Thread: TTS that sounds less fake (/showthread.php?tid=694)
Pages:
1
2
Re: TTS that sounds less fake - macropoint - 10-07-2026
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.
Re: TTS that sounds less fake - deltastation - 10-08-2026
Interesting, I hadn't tried that. That matches what I saw on dual 3090.
Re: TTS that sounds less fake - deltagrid - 10-08-2026
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.
Re: TTS that sounds less fake - cobaltspark - 10-08-2026
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.
Re: TTS that sounds less fake - kernelpeak - 10-10-2026
Maybe, but I had the opposite result. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit.