LLMs

You can integrate VNTranslator with popular LLMs through APIs for advanced features or via the web browser for free access

Free LLM Integration via Web Browser

No API configuration is required

Access LLM directly using the integrated web browser. You need to log in to each respective LLM service through the browser. Please note that some LLM services might require specific configurations or regional access. Using a VPN may sometimes result in the website failing to load.

Name	Combine Prompt	Stream	Automation
ChatGPT Web	✅	✅	✅
GeminiAI Web	✅	✅	✅
ClaudeAI Web	✅	✅	✅
MistralAI Web	✅	✅	✅
DeepSeek Web	✅	✅	✅
Grok Web	✅	✅	✅

---

Integrating LLM via API

Name	System Prompt	Stream	Context History
OpenAI API v2.x	✅	✅	✅
GeminiAI API v2.x	✅	❌	✅
ClaudeAI API v1.x	✅	✅	✅
MistralAI API v1.x	✅	✅	✅
DeepSeek API v1.x	✅	✅	✅
Grok API v1.x	✅	✅	✅
-------------------------	-	-	-
OpenAI Conversation v1.3 (legacy)	✅	✅	✅
OpenAI Translate v1.3 (legacy)	❌	❌	❌
GeminiAI v1.1 (legacy)	❌	❌	❌

You can set the LLM parameter in the MT Settings. To open MT Settings:

• In the Launcher: Menubar -> Translator -> Double-click on the translator option

System Prompt

This feature allows you to customize the initial instruction or guidance provided to the translation system. Use it to fine-tune the behavior and tone of translations.

Stream

Enables real-time streaming of translations, providing results progressively instead of waiting for the entire translation to complete.

Context History

This feature helps improve translation accuracy by considering the context of previously translated content.

• Context Source Choose the source for retrieving context:

  • New Translation History: The context will be derived from the most recent translation history in the current session.

  • Translation Memory: The context will use stored translation memory entries.

• Max Context Entries Set the maximum number of previous entries to be used as context for the translation. Note: The more entries you include, the higher the number of tokens that will be used, which may increase processing time and cost when using the translation API.

Links

• OpenAI - https://platform.openai.com

  • Models: https://platform.openai.com/docs/models#models-overview

• GeminiAI - https://aistudio.google.com

  • Models: https://ai.google.dev/gemini-api/docs/models/gemini

• ClaudeAI - https://console.anthropic.com

  • Models: https://docs.anthropic.com/en/docs/about-claude/models

• MistralAI - https://console.mistral.ai

  • Models: https://docs.mistral.ai/getting-started/models/models_overview

• DeepSeek - https://platform.deepseek.com

  • Models: https://api-docs.deepseek.com/quick_start/pricing

• GrokAI - https://console.x.ai

  • Models: https://docs.x.ai/docs/models

---

Offline (Run LLMs Locally)

• ✅ LM Studio (Recommended)

  • Download and Install LM Studio from https://lmstudio.ai/

  • Download model and load it in LM Studio

  • Start the server in LM Studio

  • Enter the model name in MT settings

• ✅ GPT4All

  • Download and Install GPT4All from https://www.nomic.ai/gpt4all

---

Content Filtering and Restrictions

LLM services like ChatGPT, GeminiAI and ClaudeAI have content filters that block:

• Explicit, harmful, or offensive content

• Text that violates the AI provider’s rules or terms of service

• Sensitive or restricted material, such as copyrighted content

What Happens with Restricted Content?

If the text you submit is flagged:

• The LLM might refuse to translate it

• You may receive an error message or a generic response instead of the translation

Tips to Avoid Issues

• Try Different Model or Version: If one model flags your text, try switching to another model or version. Note that newer versions often have stricter filters

• Experiment with Prompt Engineering: You can also search online for prompt engineering tips that have worked for others. Be careful to follow the AI provider's terms of service when doing this.