[Tools] SLR Translator - Offline JP to EN Translation for RPG Maker VX, VX Ace, MV, and MZ

[Shisaye]

(I so rarely update this lately that I might as well make notes from now on besides just changing the changelog)

1.128: Added support for a newish MZ plugin that places notes stacked on top of dialogue. It's kinda hard to read with Latin characters because it's super small, but I guess still better than leaving it Japanese.

I've also added preview screenshots of the tool, which I should have probably done earlier, but I basically thought everyone knows what Translator++ looks like and I kept the core design largely the same. (Except I changed the color palette to no longer burn your eyes out.)

 

[Shisaye]

I've released v1.129.
"Normal" Automatic Word Wrapping will no longer preserve empty lines at the end of a cell.
Meaning if the cell to be wrapped for some reason has a bunch of random linebreaks at the end it will no longer keep them and make empty dialogue boxes for them. I specify "normal" because I purposely did not apply it for word wrapping of scripts/plugins, just in case there's a weird one out there that needs a linebreak at the end. And this will not touch purposely empty cells by the dev.

If you use the Automatic Word Wrapping button, you can now type in "cwrapable" to copy all original text to Initial Translations if it matches the requirements for "normal" word wrapping.
The point of that is so you can wrap dialogue boxes you didn't actually translate/change, for example because you are parsing the translation project of someone else.
I've also added the option to type in "ceverything", which will copy ALL original text to Initial Translations in case you want that for whatever reason. (It will also copy scripts, red tagged cells, etc.)

Edit: I forgot to mention, "cwrapable" and "ceverything" will only process empty rows, meaning you can still use them even if you've already translated/changed stuff. It will not overwrite your changes.

 

[Jelly-filled Donut]

So... how good is the translation?
んで？例の自動翻訳ってどのくらい通じるの？

 

[Jelly-filled Donut]

It's kinda hard to read with Latin characters because it's super small, but I guess still better than leaving it Japanese.（redacted）

Then you might want to use sans-serif fonts instead for better legibility. Btw, is the machine uses Hepburn romanization?

 

[Shisaye]

So... how good is the translation?
んで？例の自動翻訳ってどのくらい通じるの？

Better than Google Translate, worse than DeepseekV3.
It struggles with pronouns and sometimes looses the plot on who is the one talking, who is the owner of an object, or if what is talked about is an object or a person.

Technically this can be used with LinguaGacha, since it can work with the .trans file format and that would allow you to use whatever LLM you like, but there could be errors, because my tagging system will no longer be accurate.

Then you might want to use sans-serif fonts instead for better legibility. Btw, is the machine uses Hepburn romanization?

I tend to use Ultra Condensed font because it's hard to make automatically translated English fit menus. It just takes too much space.
The tool includes a dictionary that also displays hepburn romanization, but I'm not sure if Sugoi uses hepburn. Most of the time it will do literal translations.

 

[Shisaye]

Alright so nothing about this is "sure", yet, it might just not work, but essentially, big change of plans.
The administrator has convinced me to significantly update this project after all.

I will "try" to add universal support for all common LLM apis, most importantly the OpenRouter service, which means it will be possible to use SLR Translator with whatever online LLM you want and you will be able to use the free dalie requests as well.
I also have plans further down the line to add support for LLM Studio, which will allow you to use whatever locally hosted LLM you want.

I will add an options menu to specify url, api key, model, temperature, system prompt, user prompt, and request size. They will all go through the SLR translation wrapper pipeline, which means all tagging and error checking will work exactly the same as it does for Sugoi except it will not use my dictionary system. (Since that is tailored towards SugoiV4.)

But I currently only plan to actually test stuff with the DeepSeek-chat-v3-0324 and DeepSeek-chat-v3-0324:free models, if you choose to use a different model, you're on your own.

Edit: I should mention, this will not happen overnight, adding stable support will probably take months. I don't just need to write the new code I need to run a lot of tests. These "AI" aren't particularly consistent in their responses, even if you turn the temperature way down.

 

[Vice]

Alright so nothing about this is "sure", yet, it might just not work, but essentially, big change of plans.
The administrator has convinced me to significantly update this project after all.

I will "try" to add universal support for all common LLM apis, most importantly the OpenRouter service, which means it will be possible to use SLR Translator with whatever online LLM you want and you will be able to use the free dalie requests as well.
I also have plans further down the line to add support for LLM Studio, which will allow you to use whatever locally hosted LLM you want.

I will add an options menu to specify url, api key, model, temperature, system prompt, user prompt, and request size. They will all go through the SLR translation wrapper pipeline, which means all tagging and error checking will work exactly the same as it does for Sugoi except it will not use my dictionary system. (Since that is tailored towards SugoiV4.)

But I currently only plan to actually test stuff with the DeepSeek-chat-v3-0324 and DeepSeek-chat-v3-0324:free models, if you choose to use a different model, you're on your own.

Edit: I should mention, this will not happen overnight, adding stable support will probably take months. I don't just need to write the new code I need to run a lot of tests. These "AI" aren't particularly consistent in their responses, even if you turn the temperature way down.

Nice to see the project ongoing like this, I might request for a TL later on for other projects of mine.

 

[Shisaye]

Progress update.
I think I've finally reached a point at which the result of the new translation engine seems better to me than normal SLR.
Prototype 19 was still pretty underwhelming, but now with my new prototype 21 it's actually "sometimes" better.
(Used with DeepseekV3, but my engine supports every LLM including locally hosted ones.)
Here's a comparison:

Unless I hit some huge roadblock now I "should" be able to release the first version soon so people can play around with it.
I'm just hesitant to just throw prototypes out there because this costs money and I don't want to find out I had some really dumb mistakes that drained someones entire credit balance by looping requests or something like that.

 

[Ticsol_daok9]

This is amazing! I seriously can't believe a program like this could work in different versions of RPG Maker, even the old ones like VX. It will certainly be useful. Thanks for sharing

 

[Ticsol_daok9]

(I so rarely update this lately that I might as well make notes from now on besides just changing the changelog)

1.128: Added support for a newish MZ plugin that places notes stacked on top of dialogue. It's kinda hard to read with Latin characters because it's super small, but I guess still better than leaving it Japanese.
View attachment 70682

I've also added preview screenshots of the tool, which I should have probably done earlier, but I basically thought everyone knows what Translator++ looks like and I kept the core design largely the same. (Except I changed the color palette to no longer burn your eyes out.)

I suggest you use the Manrope font. I think it's pretty readable even in small sizes. Sadly the preview website is dead. It was http://manropefont.com/ , from which I downloaded it years ago.
Here's the latest version with italics included.
https://github.com/cssobral2013/manrope

EDIT: Nevermind. It is a bit confusing or distracting to read at 16 px.
It's a good multipurpose font nonetheless.

 

[Shisaye]

I suggest you use the Manrope font. I think it's pretty readable even in small sizes. Sadly the preview website is dead. It was http://manropefont.com/ , from which I downloaded it years ago.
Here's the latest version with italics included.
https://github.com/cssobral2013/manrope

EDIT: Nevermind. It is a bit confusing or distracting to read at 16 px.
It's a good multipurpose font nonetheless.

Hm... I'll look into it, but in the end I'll always end up using Stint Ultra condensed regular again.
I just don't know any font that can cramp so much text into so little space while still being "somewhat" readable.

(Specifically talking about menu entries only meant to have 1 or 2 moonrunes.)

Edit: Although I admit I should be less lazy and not just apply the font to everything, but instead only apply it where it's actually needed.
The problem with that is just that devs love their custom menus and so I can't really automate that. It's trial and error for every new game...

 

[Shisaye]

Being at prototype 28 29 now, I think it's fair to say that I'm just never going to be happy with it and if I continue like this DSLR is not going to be out before I eventually die from an energy drink overdose.

I need some second opinions.

If you are interested in the DSLR format, meaning using SLR Translator with other LLMs. (The focus right now being on the latest experimental build of DeepSeek.)
And you have actually used complex LLMs before. PM me. (Start Conversation.)
I will explain you the current translation process and available options, and send you the latest prototype for evaluation.

You can then tell me if you believe this is usable for a general audience or not.

THE BIG FAT DISCLAIMER:
DSLR is experimental in nature and not properly tested at all. Unless you have an absolute monster of a rig there is no way to use DSLR without spending money. There is absolutely no guarantee that you get a usable result. You need to understand the cost and risk of using AI and you need to make sure that the api key you use can only use credits you are willing to loose.