+- 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 for Kimi (/showthread.php?tid=547)
Pages:
1
2
TTS that sounds less fake for Kimi - cobaltspark - 09-29-2026
Spent some time on this today and wanted to compare notes.
I've gone back and forth between vLLM and TensorRT-LLM for Phi. The interesting difference for me has been consumer GPUs.
What would you pick if you had to live with it for a few months?
For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.
Re: TTS that sounds less fake for Kimi - visionforge - 09-29-2026
Interesting, I hadn't tried that. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: TTS that sounds less fake for Kimi - kernelpeak - 09-29-2026
I don't think that's the whole story. I get why that seems right, but on GB200 the bottleneck felt elsewhere.
Re: TTS that sounds less fake for Kimi - bytegarden73 - 09-30-2026
Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up before throughput collapsed.
Re: TTS that sounds less fake for Kimi - macropoint - 10-01-2026
same here on my side.
Re: TTS that sounds less fake for Kimi - cobaltspark - 10-04-2026
that fixed it for me too.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.
Re: TTS that sounds less fake for Kimi - mellowstream - 10-04-2026
I hit almost the same issue last night.
Re: TTS that sounds less fake for Kimi - bytegarden73 - 10-04-2026
Quote:I hit almost the same issue last night.
What worked for me was pretty simple. On mini PC, the easiest win is often to back off the aggressive settings and see whether the problem survives. Once you know the plain path works, then add the faster path back in piece by piece.
Re: TTS that sounds less fake for Kimi - plainline - 10-05-2026
Quote:Quote:I hit almost the same issue last night.
I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Llama and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.
Re: TTS that sounds less fake for Kimi - quiethouse - 10-05-2026
A couple things I'd check first. If you're on TensorRT-LLM, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.