A production translation app used offline and online translation with speech recognition support created using Flutter and Genkit.
Dart
2
6 commits
updated Oct 16, 2026
A beautiful Flutter translation app with offline and online modes, voice-to-text support, and AI-powered insights via Genkit.
lango/
├── lib/
│ ├── core/ # Theme, constants, utilities
│ ├── models/ # Data models
│ ├── services/ # Translation, speech, Genkit AI services
│ ├── viewmodels/ # MVVM ViewModels
│ └── views/ # Screens and widgets
├── backend/ # Genkit Node.js AI backend
│ ├── src/index.ts # Genkit flows
│ └── hy_mt_service.py # HY-MT1.5 Python service
└── assets/
└── models/ # Vosk speech models
cd D:\Yards\Lango
flutter pub get
Download vosk-model-small-en-us-0.15.zip from https://alphacephei.com/vosk/models
and place it in assets/models/.
For Windows, install Vosk native binaries:
dart run vosk_flutter_service install -t windows
cd backend
npm install
cp .env.example .env
# Edit .env and set GOOGLE_GENAI_API_KEY
npm run dev
The Genkit server runs on http://localhost:3400.
cd backend
pip install -r requirements.txt
python hy_mt_service.py
Runs on http://localhost:3401. Without this, offline mode uses Genkit AI fallback.
flutter run
| Mode | Engine | When Used |
|---|---|---|
| Online | Cloud translation API | Internet available |
| Offline | Tencent HY-MT1.5 | No internet or forced offline |
| Auto | Switches automatically | Default |
Language, TranslationRecord, TranslationModeAppViewModel, TranslateViewModel (via Provider)OnlineTranslationService, OfflineTranslationService, VoskSpeechService, GenkitAiService| Flow | Purpose |
|---|---|
hyMtTranslateFlow | Offline HY-MT1.5 translation |
explainTranslationFlow | AI translation explanations |
contextualTranslateFlow | Context-aware translation |
suggestPhrasesFlow | Topic-based phrase suggestions |
Private project.
A production translation app used offline and online translation with speech recognition support created using Flutter and Genkit.
Dart
2
6 commits
updated Oct 16, 2026
A beautiful Flutter translation app with offline and online modes, voice-to-text support, and AI-powered insights via Genkit.
lango/
├── lib/
│ ├── core/ # Theme, constants, utilities
│ ├── models/ # Data models
│ ├── services/ # Translation, speech, Genkit AI services
│ ├── viewmodels/ # MVVM ViewModels
│ └── views/ # Screens and widgets
├── backend/ # Genkit Node.js AI backend
│ ├── src/index.ts # Genkit flows
│ └── hy_mt_service.py # HY-MT1.5 Python service
└── assets/
└── models/ # Vosk speech models
cd D:\Yards\Lango
flutter pub get
Download vosk-model-small-en-us-0.15.zip from https://alphacephei.com/vosk/models
and place it in assets/models/.
For Windows, install Vosk native binaries:
dart run vosk_flutter_service install -t windows
cd backend
npm install
cp .env.example .env
# Edit .env and set GOOGLE_GENAI_API_KEY
npm run dev
The Genkit server runs on http://localhost:3400.
cd backend
pip install -r requirements.txt
python hy_mt_service.py
Runs on http://localhost:3401. Without this, offline mode uses Genkit AI fallback.
flutter run
| Mode | Engine | When Used |
|---|---|---|
| Online | Cloud translation API | Internet available |
| Offline | Tencent HY-MT1.5 | No internet or forced offline |
| Auto | Switches automatically | Default |
Language, TranslationRecord, TranslationModeAppViewModel, TranslateViewModel (via Provider)OnlineTranslationService, OfflineTranslationService, VoskSpeechService, GenkitAiService| Flow | Purpose |
|---|---|
hyMtTranslateFlow | Offline HY-MT1.5 translation |
explainTranslationFlow | AI translation explanations |
contextualTranslateFlow | Context-aware translation |
suggestPhrasesFlow | Topic-based phrase suggestions |
Private project.