I am using LangFuse currently, but I'm not liking the integration with Python, it does a lot of things automatically which is good, but trying to change things is being a nightmare

I need to clone voice of people users but it's not feasible to do it with the old voice cloning AI models that need a lot of training(+30 min). I've tried a few 0-shot AI models that came out last year and this year but none of them are reliable enough. The ideal scenario would be being able to...