{"id":31009482,"url":"https://github.com/codervivek5/acko-voice-assistant","last_synced_at":"2025-09-13T04:38:52.481Z","repository":{"id":314221378,"uuid":"1054629193","full_name":"codervivek5/Acko-Voice-Assistant","owner":"codervivek5","description":null,"archived":false,"fork":false,"pushed_at":"2025-09-11T06:02:03.000Z","size":130,"stargazers_count":0,"open_issues_count":1,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-09-11T09:39:23.383Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://acko-voice-assistant.vercel.app","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/codervivek5.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-09-11T05:45:42.000Z","updated_at":"2025-09-11T06:02:06.000Z","dependencies_parsed_at":"2025-09-11T09:39:42.418Z","dependency_job_id":"0cd66d3e-5a27-4c0f-835f-16e194e91e22","html_url":"https://github.com/codervivek5/Acko-Voice-Assistant","commit_stats":null,"previous_names":["codervivek5/acko-voice-assistant"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/codervivek5/Acko-Voice-Assistant","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codervivek5%2FAcko-Voice-Assistant","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codervivek5%2FAcko-Voice-Assistant/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codervivek5%2FAcko-Voice-Assistant/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codervivek5%2FAcko-Voice-Assistant/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/codervivek5","download_url":"https://codeload.github.com/codervivek5/Acko-Voice-Assistant/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codervivek5%2FAcko-Voice-Assistant/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274920031,"owners_count":25373953,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-09-13T02:00:10.085Z","response_time":70,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-09-13T04:38:51.282Z","updated_at":"2025-09-13T04:38:52.470Z","avatar_url":"https://github.com/codervivek5.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🏥 Acko Medical Voice Assistant\n\nAn AI-powered real-time voice transcription and reflexive question generator specifically designed for Medical Examination Reports (MER) in health insurance underwriting. Built for the ACKO hackathon to enhance doctor-customer interactions during tele/video consultations.\n\n## ✨ Features\n\n### 🎤 Enhanced Speech Recognition\n- **Real-Time Transcription**: High-accuracy speech-to-text with Indian accent support\n- **Bilingual Support**: Hindi + English with dynamic language switching\n- **Indian Accent Recognition**: Optimized for diverse Indian dialects and pronunciation\n- **Speaker Annotation**: Automatic Doctor/Patient identification\n- **Confidence Scoring**: Real-time accuracy feedback and language detection\n- **Advanced Statistics**: Duration, word count, language switches, and confidence metrics\n\n### 🤖 Medical AI Intelligence\n- **Reflexive Question Generation**: Context-aware medical questions for insurance underwriting\n- **Sentiment Analysis**: Detect patient distress, confusion, or emotional state\n- **Risk Assessment**: Automatic flagging of high-risk medical indicators\n- **Medical Context Extraction**: Identify symptoms, conditions, and medications\n- **Question Categorization**: Binary, Scale, and Open-ended question types\n- **Priority-based Display**: High, Medium, Normal priority questions\n- **Comprehensive Medical Summaries**: Professional MER reports with risk flags\n\n### 🧠 Session Memory \u0026 Context\n- **Multi-day Context Retention**: Maintain conversation context across sessions\n- **Session History Search**: Find and load previous consultations\n- **Context-aware Questions**: Generate questions based on prior session data\n- **Risk Level Tracking**: Monitor patient risk across multiple consultations\n- **Session Analytics**: Track consultation patterns and outcomes\n- **Cloud Storage**: Secure Firebase integration for session persistence\n\n### 🎨 Medical Doctor Interface\n- **Real-time Annotations**: Live speaker identification and medical insights\n- **Interactive Question Management**: Select, edit, and swap suggested questions\n- **Visual Risk Indicators**: Color-coded risk levels and priority alerts\n- **Professional Medical Theme**: Healthcare-focused design with medical icons\n- **Responsive Design**: Optimized for various devices and screen sizes\n- **Accessibility**: Keyboard navigation and screen reader support\n\n## 🏆 Hackathon Requirements Met\n\n### ✅ Mandatory Requirements\n1. **Real-Time Voice Transcription**\n   - Robust speech-to-text with Indian accent support\n   - Bilingual capabilities (Hindi + English)\n   - Dynamic language switching during sessions\n\n2. **Reflexive Question Generation**\n   - Medical-specific NLU processing\n   - Clinically appropriate, context-aware questions\n   - Emotion/sentiment detection and alerts\n   - Multiple question types (open-ended, binary, scale-based)\n\n3. **Interactive Doctor Interface**\n   - Real-time transcribed text with speaker annotations\n   - Accept/edit/swap suggested questions\n   - Visual cues and organized interaction flow\n\n### ✅ Good-to-Have Features\n4. **Consultation Summary Generator**\n   - Automatic session summaries with key responses\n   - Risk flags and missing information alerts\n   - Professional medical report formatting\n\n5. **Context Retention \u0026 Adaptability**\n   - Session memory across conversation turns\n   - Multi-day conversation support\n   - Adaptive follow-up questions based on prior sessions\n\n6. **System Scalability and Performance**\n   - Low-latency transcription and response generation\n   - High concurrency support for multiple sessions\n   - Optimized for real-time medical consultations\n\n## 🚀 Quick Start\n\n### Prerequisites\n- Node.js 16+ and npm\n- Modern browser with speech recognition support (Chrome, Edge recommended)\n- Firebase project for data persistence\n- Google Gemini API key for AI features\n\n### Installation\n\n1. **Clone the repository**\n   ```bash\n   git clone https://github.com/your-username/acko-voice-assistant.git\n   cd acko-voice-assistant\n   ```\n\n2. **Install dependencies**\n   ```bash\n   npm install\n   ```\n\n3. **Environment Setup**\n   Create a `.env` file in the root directory:\n   ```env\n   VITE_FIREBASE_API_KEY=your_firebase_api_key\n   VITE_FIREBASE_AUTH_DOMAIN=your_project.firebaseapp.com\n   VITE_FIREBASE_PROJECT_ID=your_project_id\n   VITE_FIREBASE_STORAGE_BUCKET=your_project.appspot.com\n   VITE_FIREBASE_MESSAGING_SENDER_ID=your_sender_id\n   VITE_FIREBASE_APP_ID=your_app_id\n   VITE_GEMINI_API_KEY=your_gemini_api_key\n   ```\n\n4. **Start the development server**\n   ```bash\n   npm run dev\n   ```\n\n5. **Open your browser**\n   Navigate to `http://localhost:5173`\n\n## 🏗️ Project Structure\n\n```\nsrc/\n├── components/\n│   └── SpeechRecognition.jsx    # Main speech recognition component\n├── config/\n│   ├── firebase.js              # Firebase configuration\n│   └── gemini.js                # Gemini AI configuration\n├── services/\n│   ├── aiService.js             # AI service for questions and summaries\n│   └── databaseService.js       # Database operations\n├── App.jsx                      # Main application component\n├── App.css                      # Application styles\n├── index.css                    # Global styles and CSS variables\n└── main.jsx                     # Application entry point\n```\n\n## 🔧 Configuration\n\n### Firebase Setup\n1. Create a new Firebase project at [Firebase Console](https://console.firebase.google.com)\n2. Enable Firestore Database\n3. Configure security rules for your use case\n4. Add your Firebase config to the `.env` file\n\n### Gemini AI Setup\n1. Get your API key from [Google AI Studio](https://makersuite.google.com/app/apikey)\n2. Add the key to your `.env` file as `VITE_GEMINI_API_KEY`\n\n## 📱 Usage\n\n### Starting a Session\n1. Click \"Start Recording\" to begin speech recognition\n2. Speak clearly into your microphone\n3. Watch real-time transcription appear\n4. Use the settings panel to adjust language preferences\n\n### Generating Questions\n- Questions are automatically generated as you speak\n- Click the copy button to copy questions to clipboard\n- Questions are contextually relevant to your consultation\n\n### Session Management\n- Click \"Generate Summary\" to create a session summary\n- Use \"Save Session\" to store the session in Firebase\n- Export sessions as JSON files for external use\n- View recent sessions in the sidebar\n\n### Settings \u0026 Customization\n- Language selection for speech recognition\n- Mute/unmute functionality\n- Real-time statistics display\n- Error handling and notifications\n\n## 🛠️ Development\n\n### Available Scripts\n- `npm run dev` - Start development server\n- `npm run build` - Build for production\n- `npm run preview` - Preview production build\n- `npm run lint` - Run ESLint\n\n### Code Style\n- ESLint configuration for consistent code quality\n- Modern React patterns with hooks\n- CSS custom properties for theming\n- Responsive design principles\n\n## 🔒 Security \u0026 Privacy\n\n- **Local Processing**: Speech recognition runs in the browser\n- **Secure Storage**: Firebase provides encrypted cloud storage\n- **API Security**: Environment variables protect API keys\n- **Data Privacy**: No data is shared with third parties except configured services\n\n## 🌐 Browser Support\n\n- **Chrome**: Full support (recommended)\n- **Edge**: Full support\n- **Firefox**: Limited speech recognition support\n- **Safari**: Limited speech recognition support\n\n## 📊 Performance\n\n- **Optimized Bundle**: Vite for fast development and building\n- **Lazy Loading**: Components load as needed\n- **Efficient State Management**: React hooks for optimal performance\n- **Caching**: Firebase caching for improved data access\n\n## 🤝 Contributing\n\n1. Fork the repository\n2. Create a feature branch (`git checkout -b feature/amazing-feature`)\n3. Commit your changes (`git commit -m 'Add amazing feature'`)\n4. Push to the branch (`git push origin feature/amazing-feature`)\n5. Open a Pull Request\n\n## 📄 License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## 🆘 Support\n\n- **Documentation**: Check this README and inline code comments\n- **Issues**: Report bugs and request features via GitHub Issues\n- **Discussions**: Join community discussions for help and ideas\n\n## 🔮 Roadmap\n\n- [ ] Multi-user support with authentication\n- [ ] Advanced AI insights and analytics\n- [ ] Integration with EHR systems\n- [ ] Mobile app development\n- [ ] Voice commands for navigation\n- [ ] Custom question templates\n- [ ] Session collaboration features\n\n## 🙏 Acknowledgments\n\n- **Google**: Speech Recognition API and Gemini AI\n- **Firebase**: Backend infrastructure\n- **Lucide React**: Beautiful icons\n- **Vite**: Fast build tooling\n- **React**: Frontend framework\n\n---\n\n**Made with ❤️ for healthcare professionals**","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcodervivek5%2Facko-voice-assistant","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcodervivek5%2Facko-voice-assistant","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcodervivek5%2Facko-voice-assistant/lists"}