PopLingo

v1.0.1 繁體中文

Translation engine setup

PopLingo speaks the OpenAI-compatible API, so any service that offers /chat/completions works. Pick a service in Settings, paste your key, done.

Where to configure

Right-click the tray icon → Settings → the Translation tab.

FieldDescription
ProviderDropdown. Choosing one auto-fills the API URL and model list.
API URLEditable (used with the "Custom…" provider).
API KeyYour key from the provider.
ModelDropdown, but you can type any model name the provider offers.
Get API keyOpens the provider's signup page.

Option A: DeepSeek (recommended)

Good Chinese and English quality at a low price; the best default choice.

  1. Sign up at platform.deepseek.com
  2. Open "API keys" → create a key and copy it
  3. In PopLingo Settings:
    FieldValue
    ProviderDeepSeek
    API URLhttps://api.deepseek.com
    Modeldeepseek-flash (cheap and fast)
    or deepseek-v4-pro (higher quality)
  4. Click Save and type something in the card to test

DeepSeek is a paid service billed by usage. Translation uses very few tokens, so typical monthly cost is tiny.

Option B: other cloud providers

Provider API URL Example model
OpenAIhttps://api.openai.com/v1gpt-4o-mini
Alibaba Qwen (DashScope)https://dashscope.aliyuncs.com/compatible-mode/v1qwen-plus
Zhipu GLMhttps://open.bigmodel.cn/api/paas/v4glm-4-flash
Kimi (Moonshot)https://api.moonshot.cn/v1moonshot-v1-8k
SiliconFlowhttps://api.siliconflow.cn/v1deepseek-ai/DeepSeek-V3
Tencent Hunyuanhttps://api.hunyuan.cloud.tencent.com/v1hunyuan-turbo
Volcengine Doubaohttps://ark.cn-beijing.volces.com/api/v3doubao-1.5-lite-32k
MiniMaxhttps://api.minimax.chat/v1abab6.5s-chat
Groqhttps://api.groq.com/openai/v1llama-3.3-70b-versatile
Mistralhttps://api.mistral.ai/v1mistral-small-latest
OpenRouterhttps://openrouter.ai/api/v1openai/gpt-4o-mini

All of these are built into the dropdown, so you never type the URL by hand. Model names change over time, so the model field accepts free text.

Option C: fully local (Ollama)

Don't want to send anything to the cloud? Run a model on your own machine with Ollama — free, offline, and nothing leaves your PC.

Steps

  1. Download and install Ollama from ollama.com/download
  2. In Command Prompt, pull a model (about 4–6 GB, one time):
    ollama pull qwen2.5:7b
  3. Confirm it downloaded:
    ollama list
  4. In PopLingo Settings:
    FieldValue
    ProviderOllama (local)
    API URLhttp://localhost:11434/v1
    API Keyollama (ignored locally, any value works)
    Modelqwen2.5:7b

Choosing a model

ModelMemoryNotes
qwen2.5:3b~4 GBLightest, acceptable quality
qwen2.5:7b~8 GBRecommended balance of quality and speed
qwen2.5:14b~16 GBBetter quality, needs a stronger machine
gemma3:4b~5 GBDecent multilingual support

Note: the first response from a local model is slow (it has to load into memory), and quality is usually a bit below cloud models like DeepSeek or GPT. Best for privacy-conscious users, or if you'd rather not pay.

LM Studio

You can also use LM Studio: start its local server, then pick "LM Studio (local)" in Settings. The API URL is http://localhost:1234/v1.

Languages and style

FieldDescription
Source languageDefaults to "Auto detect" and lets the model decide.
Target languageDefaults to English.
Second languageUsed when the source already is the target language. "(None)" disables it. See the guide.
StyleAcademic (default) / Business / Casual.
Delay (ms)How long to wait after you stop typing before translating. Default 500.

Privacy

Only the text you type is sent, and only to the API you configured. PopLingo itself collects nothing and contains no tracking or telemetry. With a local Ollama model, your text never leaves your computer.