I'm curious whether you can get https://platform.nuenki.app (my deep translation service; I'm just polishing it before release) to run into "too sexual". It's designed to be resilient to that kind of thing, and it works well in my testing, but maybe you have some better "stress test" content than me!
I don't use hosted AI much. But one of the reasons I like AI is that I can ask it something like "Hmm I don't like how this sounds, can you formulate it another way, more colloquial?" and it'll take that into account. Or what I often get is that it translates "you" to singular when I need plural and vice versa. In most languages that differs but not in English.
I can't deal with any of the in editor tools. I'd love something that handled inputting changes (with manual review!) while still giving me 100% control over the context and actually doing as its told.
I've done a lot of research into LLM translation for my product[0], and I'm currently working on a deep translation service that provides reliably human-level translations.
I don't know what model you're using, but GPT-4.1 is probably the best for your use case - it's in the top few % for nearly every language, and has a low standard deviation, while also being relatively low latency and low cost.
This is a neat topic. I've only ever done this once.
A friend of mine had made a spreadsheet of fusion 360 shortcuts, so I made a little webapp for use at school: https://fusion.alexcj.co.uk/
I made it use a custom stylesheet for printing, as they describe in the article, so that it produced a nice worksheet - though in retrospect, I probably ought to have made it denser when printed!
reply