{"id":49474026,"url":"https://github.com/aydrian/teleprompter","last_synced_at":"2026-04-30T18:04:28.866Z","repository":{"id":309916337,"uuid":"1037072653","full_name":"aydrian/teleprompter","owner":"aydrian","description":"A real-time, voice-synchronized teleprompter application built with React, LiveKit, and speech-to-text technology.","archived":false,"fork":false,"pushed_at":"2026-04-27T16:45:27.000Z","size":331,"stargazers_count":2,"open_issues_count":0,"forks_count":1,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-27T18:33:39.339Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/aydrian.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2025-08-13T03:01:42.000Z","updated_at":"2026-04-27T16:45:24.000Z","dependencies_parsed_at":"2025-12-15T19:04:36.578Z","dependency_job_id":null,"html_url":"https://github.com/aydrian/teleprompter","commit_stats":null,"previous_names":["aydrian/teleprompter"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/aydrian/teleprompter","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aydrian%2Fteleprompter","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aydrian%2Fteleprompter/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aydrian%2Fteleprompter/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aydrian%2Fteleprompter/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aydrian","download_url":"https://codeload.github.com/aydrian/teleprompter/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aydrian%2Fteleprompter/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32472424,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-30T13:12:12.517Z","status":"ssl_error","status_checked_at":"2026-04-30T13:12:06.837Z","response_time":57,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":"2026-04-30T18:04:27.563Z","updated_at":"2026-04-30T18:04:28.852Z","avatar_url":"https://github.com/aydrian.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🎙️ LiveKit Teleprompter\n\nA real-time, voice-synchronized teleprompter application built with React, LiveKit, and speech-to-text technology. The teleprompter automatically advances as you speak, providing a seamless presentation experience.\n\n## ✨ Features\n\n- 🎙️ **Real-time Speech Recognition**: Automatic speech-to-text transcription using Deepgram\n- 📜 **Smart Text Synchronization**: Teleprompter advances based on your spoken words\n- 🔄 **LiveKit WebRTC Integration**: Low-latency audio streaming and processing\n- ✏️ **Script Editor**: Built-in editor for creating and modifying scripts\n- 🎯 **Sentence-based Tracking**: Intelligent matching of speech to script sentences\n- 🔇 **Noise Cancellation**: Krisp noise filter for cleaner audio input\n- ⚡ **Real-time Processing**: Instant response to speech with RPC communication\n\n## 🏗️ Architecture\n\nThe application consists of two main components:\n\n### Web Application\n\n- **Framework**: React Router v7 with server-side rendering\n- **UI**: React with Tailwind CSS and Radix UI components\n- **WebRTC**: LiveKit client for real-time communication\n- **State Management**: React hooks and context providers\n\n### Agent Service\n\n- **Framework**: LiveKit Agents SDK\n- **Speech-to-Text**: Deepgram STT with Silero VAD\n- **Communication**: RPC over LiveKit data channels\n- **Processing**: Real-time transcript generation and transmission\n\n## 📋 Prerequisites\n\n- Node.js 18+ and pnpm\n- [LiveKit Cloud account](https://cloud.livekit.io) (free tier available)\n- API Keys:\n  - LiveKit API key and secret (from LiveKit Cloud dashboard)\n  - Deepgram API key (for speech-to-text)\n\n## 🚀 Installation\n\n1. Clone the repository:\n\n```bash\ngit clone https://github.com/aydrian/teleprompter.git\ncd teleprompter\n```\n\n2. Install dependencies:\n\n```bash\npnpm install\n```\n\n3. Set up environment variables:\n\n```bash\ncp .env.example .env\n```\n\nEdit `.env` with your configuration:\n\n```env\n# LiveKit Cloud Configuration\nLIVEKIT_URL=wss://your-project.livekit.cloud\nLIVEKIT_API_KEY=your-api-key\nLIVEKIT_API_SECRET=your-api-secret\n\n# Deepgram Configuration\nDEEPGRAM_API_KEY=your-deepgram-key\n\n# Optional: OpenAI for alternative STT\nOPENAI_API_KEY=your-openai-key\n```\n\nGet your LiveKit credentials from the [LiveKit Cloud dashboard](https://cloud.livekit.io) after creating a project.\n\n## 💻 Development\n\n### Starting the Web Application\n\n```bash\npnpm run dev\n```\n\nThe application will be available at `http://localhost:3000`\n\n### Starting the Agent\n\nIn a separate terminal:\n\n```bash\npnpm run agent:dev\n```\n\nThe agent will connect to LiveKit Cloud and wait for job assignments.\n\n## 📖 Usage\n\n1. **Open the Application**: Navigate to `http://localhost:3000`\n\n2. **Connect to Room**: Click \"Start Conversation\" to connect to the LiveKit room\n\n3. **Edit Script**:\n   - Click the Edit button to modify the teleprompter script\n   - Save your changes to update the display\n\n4. **Start Speaking**:\n   - The teleprompter will automatically highlight and advance sentences as you speak them\n   - The system matches your speech to the script with intelligent word matching\n\n5. **Controls**:\n   - **Reset**: Return to the beginning of the script\n   - **Edit**: Toggle between edit and presentation modes\n\n## ⚙️ Configuration\n\n### LiveKit Settings\n\nConfigure LiveKit connection in `app/routes/api/livekit/config.ts`:\n\n- Room settings\n- Participant permissions\n- Audio/video configuration\n\n### Agent Settings\n\nModify agent behavior in `agents/teleprompter/agent.ts`:\n\n- STT provider (Deepgram/OpenAI)\n- VAD sensitivity\n- Transcript processing logic\n\n### UI Customization\n\nCustomize the teleprompter interface in `app/components/Teleprompter.tsx`:\n\n- Font sizes and styles\n- Highlight colors\n- Animation speeds\n\n## 📁 Project Structure\n\n```\nteleprompter/\n├── agents/                 # LiveKit agent service\n│   └── teleprompter/\n│       └── agent.ts       # Main agent implementation\n├── app/\n│   ├── components/        # React components\n│   │   ├── Room.tsx      # LiveKit room wrapper\n│   │   ├── Playground.tsx # Main UI container\n│   │   └── Teleprompter.tsx # Teleprompter component\n│   ├── hooks/            # Custom React hooks\n│   │   ├── useConnection.tsx # Room connection logic\n│   │   └── useTranscriber.ts # RPC transcript handling\n│   └── routes/           # React Router routes\n│       ├── api/         # API endpoints\n│       └── home.tsx     # Main application route\n├── public/              # Static assets\n├── package.json         # Project dependencies\n├── vite.config.ts      # Vite configuration\n└── LICENSE             # MIT license\n```\n\n## 🚢 Deployment\n\n### Deploy the Web Application\n\nThe web application can be deployed to any Node.js hosting platform:\n\n#### Option 1: Traditional Node.js Server\n\n1. Build the application:\n\n```bash\npnpm run build\n```\n\n2. Start the production server:\n\n```bash\npnpm run start\n```\n\n#### Option 2: Docker Deployment\n\n```dockerfile\nFROM node:20-alpine\nWORKDIR /app\nCOPY package*.json ./\nRUN npm ci --production\nCOPY build/ ./build/\nCOPY public/ ./public/\nEXPOSE 3000\nCMD [\"npm\", \"run\", \"start\"]\n```\n\n#### Option 3: Platform-as-a-Service (PaaS)\n\nDeploy to platforms like:\n\n- Vercel\n- Netlify\n- Railway\n- Render\n- Fly.io\n- Heroku\n\n### Deploy the Agent\n\nThe agent needs to be deployed as a separate service. Options include:\n\n- Docker container\n- Kubernetes deployment\n- Cloud Run or similar serverless platforms\n- VPS with process manager (PM2, systemd)\n\nExample Dockerfile for agent:\n\n```dockerfile\nFROM node:20-slim\nWORKDIR /app\nCOPY package*.json ./\nCOPY agents/ ./agents/\nRUN npm ci --production\nCMD [\"node\", \"agents/teleprompter/agent.js\", \"start\"]\n```\n\n## 🔧 Troubleshooting\n\n### Agent Not Receiving Jobs\n\n- Ensure LiveKit Cloud project is properly configured\n- Check agent is registered: Look for \"registered worker\" in agent logs\n- Verify environment variables are set correctly with LiveKit Cloud credentials\n- Check LiveKit Cloud dashboard for active sessions and agent status\n\n### No Speech Recognition\n\n- Check microphone permissions in browser\n- Verify Deepgram API key is valid\n- Check agent logs for STT errors\n\n### Teleprompter Not Advancing\n\n- Ensure you're speaking clearly into the microphone\n- Check browser console for RPC errors\n- Verify agent is processing transcripts (check logs)\n\n## 🤝 Contributing\n\nContributions are welcome! Please feel free to submit a Pull Request.\n\n1. Fork the repository\n2. Create your feature branch (`git checkout -b feature/AmazingFeature`)\n3. Commit your changes (`git commit -m 'Add some AmazingFeature'`)\n4. Push to the branch (`git push origin feature/AmazingFeature`)\n5. Open a Pull Request\n\n## 🙏 Acknowledgments\n\n- [LiveKit](https://livekit.io) for the WebRTC infrastructure\n- [Deepgram](https://deepgram.com) for speech-to-text capabilities\n- [React Router](https://reactrouter.com) for the application framework\n- [Tailwind CSS](https://tailwindcss.com) for styling\n- [Radix UI](https://radix-ui.com) for accessible UI components\n\n## 📄 License\n\nThis project is licensed under the MIT License - see the [LICENSE](./LICENSE) file for details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faydrian%2Fteleprompter","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faydrian%2Fteleprompter","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faydrian%2Fteleprompter/lists"}