Skip to main content

Translation Settings

In this panel, you can set the source language and target language, as well as select and configure the service engine used to complete the translation.

Language Presets​

Source Language and Target Language​

  • Support Range: Built-in support for translation between more than twenty languages including English, Japanese, Simplified and Traditional Chinese, Korean, etc.
  • Auto Detection Option: When setting Source Language to "Auto", the system will automatically recognize the language of the text in the screenshot, without the need for you to manually adjust when switching games. Target Language is usually set to your native language (such as Simplified Chinese).

Translation Service Configuration​

Translation Mode​

Select the processing channel for translation requests:

  • Built-in Translation Service: Directly use the service integration built into the project, without the need for you to apply for development keys on the platform.
  • Custom Configuration: Suitable for users who have already applied for relevant platform API keys on their own, or have deployed inference models locally.

Translation Service Type​

Select which type of translation engine to use:

  • General Translation Service: Traditional machine translation based on "sentence-to-sentence", with fast response speed. Includes mainstream services such as Tencent Cloud, Microsoft Translator, Volcano Engine, Alibaba Cloud, Baidu Translate, Youdao, Google, DeepL, and Huawei. (Youdao Translation and Huawei Translation are not yet adapted)
  • LLM Large Model Service: Based on large language models, better at context understanding and tone polishing. Includes services such as OpenAI, DeepSeek, Alibaba Tongyi Qianwen, Volcano Doubao, and SiliconFlow.

Service Request Status Prompt: When selecting "Built-in" mode, if the system is loading the available interface list, a rotating loading animation will be displayed next to the dropdown box. If the request fails due to network issues, it will be displayed in red countdown text, at which point you can wait for a retry or switch to "Custom" mode.

Custom Credentials​

After selecting "Custom" mode, according to the selected service type, the following input items will be displayed:

  • API ID / Username: Some service providers (such as Baidu Translate) require providing an App ID at the same time, fill it in here.
  • API Key / Password: Fill in the API key generated by the corresponding service provider.
  • Model Name: Only valid for LLM mode. Fill in the specific model you want to use, such as deepseek-chat, gpt-4o-mini.
  • System Prompt: Only valid for LLM mode. Used to customize the translation style and requirements of the model, such as requiring the retention of specific formats or outputting more authentic localized translations.
  • Custom Interface Address: Only valid for LLM mode. If you use locally deployed Ollama, LM Studio, or proxy relay services, you can fill in the custom interface address here (such as http://localhost:11434/v1/chat/completions), leave blank to use the default interface of the selected service provider.