Privacy-first AI translation that runs entirely on your machine
Features • Quick Start • Installation • Usage • Tech Stack
Traditional translation services send your text to remote servers. Localce is different — it uses LM Studio to run AI models locally on your computer. Your data never leaves your device.
| Feature | Localce | Cloud Services |
|---|---|---|
| Privacy | ✅ 100% Local | ❌ Data sent to servers |
| Internet Required | ❌ Works offline | ✅ Always required |
| Cost | ✅ Free forever | 💰 Usually paid |
| Speed | ⚡ Instant | 🐌 Network latency |
All translations happen locally using LM Studio. No data is ever sent to external servers.
Translate between 12+ languages including English, Turkish, Spanish, French, German, Italian, Portuguese, Russian, Japanese, Chinese, Korean, and Arabic.
Translate plain text or upload files (.txt, .md, .json, .csv, .srt, and more).
Choose from Standard, Formal, Casual, or Technical tones to match your context.
Automatically save your translation history and star your favorite translations.
Modern, responsive design with dark mode support and smooth animations.
Listen to translations with built-in TTS support for multiple languages.
- LM Studio — Download and install
- Translation Model — Download a model (recommended:
HY-MT1.5-7B) - Start Local Server — Run LM Studio's local server on port
1234
# Clone
git clone https://github.com/sudoeren/localce.git && cd localce
# Install
npm install
# Start
npm run devOpen http://localhost:3000 and start translating!
git clone https://github.com/sudoeren/localce.git
cd localce
npm install
npm run devgit clone https://github.com/sudoeren/localce.git
cd localce
docker-compose up -ddocker build -t localce .
docker run -p 3000:3000 --add-host=host.docker.internal:host-gateway localce- Select source language (or Auto Detect)
- Select target language
- Choose translation tone (optional)
- Enter text
- Press
Ctrl+Enteror click Translate
- Switch to File mode
- Upload a text file
- Select target language
- Click Translate
- Download the translated file
| Shortcut | Action |
|---|---|
Ctrl+Enter |
Translate |
Ctrl+C |
Copy translation |
Create a .env.local file:
LM_STUDIO_URL=http://localhost:1234/v1/chat/completions
LM_STUDIO_MODEL=hy-mt1.5-7b/HY-MT1.5-7B-Q4_K_M.gguf
LM_STUDIO_TEMPERATURE=0.2Navigate to Settings to configure:
- LM Studio connection URL
- Model temperature
- Theme (Light/Dark/System)
- Language (English/Turkish)
| Category | Technology |
|---|---|
| Framework | Next.js 16 |
| UI Library | React 19 |
| Language | TypeScript |
| Styling | Tailwind CSS v4 |
| Components | shadcn/ui + Radix UI |
| Animations | Framer Motion |
| AI Backend | LM Studio |
localce/
├── src/
│ ├── app/ # Next.js App Router
│ │ ├── page.tsx # Main translator
│ │ ├── history/ # Translation history
│ │ ├── favorites/ # Saved translations
│ │ ├── settings/ # App settings
│ │ └── api/translate/ # Translation API
│ ├── components/ # React components
│ ├── contexts/ # React contexts
│ ├── hooks/ # Custom hooks
│ └── lib/ # Utilities
├── public/ # Static assets
├── Dockerfile # Docker config
└── docker-compose.yml # Docker Compose
Contributions are welcome! Please feel free to submit a Pull Request.
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing) - Open a Pull Request
MIT License — see LICENSE for details.
Developed by Eren Cakar