Discord Voice Translator V2 🎤🌍

A comprehensive microservices-based Discord bot that captures voice channel audio, transcribes it using GPU-accelerated Whisper, and provides real-time multi-language translation.

🚀 Features

• Real-time Voice Capture: Records individual user audio streams from Discord voice channels
• GPU-Accelerated Transcription: Uses faster-whisper with NVIDIA RTX 4000 for lightning-fast speech-to-text
• Multi-language Translation: Supports translation to English, German, Korean, and more
• Microservices Architecture: Scalable, maintainable design with independent services
• Web Dashboard: Real-time monitoring and historical analytics
• High Performance: Optimized for low-latency processing

🏗️ Architecture

Discord Voice → [Recorder] → Raw PCM → [Audio Processor] → Optimized WAV
    ↓
[Whisper Service] → Transcription → [Translator] → Multi-language
    ↓
[Transcriber] → Discord Messages + Database → [Dashboard]

Services Overview

Service	Purpose	Technology
Recorder	Discord bot + voice capture	Node.js, Discord.js
Audio Processor	PCM to WAV conversion	Python, FFmpeg
Whisper Service	GPU-accelerated transcription	Python, faster-whisper, CUDA
Translator	Multi-language translation	Python, Google/DeepL APIs
Transcriber	Workflow orchestration	Node.js, Message queues
Dashboard	Web monitoring interface	Node.js, Express, WebSockets

🛠️ Prerequisites

Hardware Requirements

• GPU: NVIDIA RTX 4000 (or compatible CUDA GPU)
• RAM: 8GB+ recommended
• Storage: 50GB+ for models and audio cache

Software Requirements

• Docker with Docker Compose
• NVIDIA Container Toolkit for GPU support
• Unraid (recommended) or Linux host

⚡ Quick Start

1. Clone the Repository

git clone <your-gitea-url>/discord-voice-translator-v2.git
cd discord-voice-translator-v2

2. Configure Environment

cp .env.example .env
# Edit .env with your API keys and settings

Required environment variables:

# Discord Bot
DISCORD_TOKEN=your_discord_bot_token
CLIENT_ID=your_bot_client_id
GUILD_ID=your_guild_id

# Database
POSTGRES_PASSWORD=your_secure_password

# Translation APIs
GOOGLE_TRANSLATE_API_KEY=your_google_api_key
DEEPL_API_KEY=your_deepl_api_key

3. Start Services

# Start core services
docker-compose up -d

# Start with admin interfaces
docker-compose --profile admin up -d

4. Verify GPU Support

# Check Whisper service GPU status
curl http://localhost:8001/health

📊 Service Endpoints

Service	Port	Health Check	Purpose
Whisper Service	8001	/health	GPU transcription
Translator	8002	/health	Multi-language translation
Dashboard	3000	/	Web monitoring
PostgreSQL	5432	-	Database
Redis	6379	-	Message queue
pgAdmin	8080	/	Database admin
Redis Commander	8081	/	Redis admin

🎮 Discord Commands

• /join - Join your voice channel and start recording
• /leave - Leave voice channel and stop recording
• /status - Show current recording status

📈 Performance Optimizations

GPU Configuration

• Model: faster-whisper large-v2 with CUDA
• Precision: float16 for optimal RTX 4000 performance
• Memory: ~2GB VRAM usage for transcription
• Speed: 2-3x real-time transcription

Audio Processing

• Input: Discord 48kHz stereo PCM
• Output: 16kHz mono WAV (optimized for Whisper)
• Conversion: FFmpeg with fallback to Python/scipy
• Cleanup: Automatic removal of processed PCM files

🗄️ Database Schema

• connections: Voice channel session tracking
• recordings: Individual user audio recordings
• transcriptions: Speech-to-text results with confidence scores
• translations: Multi-language translation results
• processing_metrics: Performance monitoring
• user_activity: Aggregated usage statistics

🔧 Development

Local Development

# Individual service development
cd services/recorder
npm install
npm run dev

# Audio processor
cd services/audio-processor  
pip install -r requirements.txt
python src/processor.py

Testing GPU Support

# Verify NVIDIA Docker runtime
docker run --rm --gpus all nvidia/cuda:11.8-base-ubuntu22.04 nvidia-smi

# Test Whisper service
docker-compose exec whisper-service python -c "import torch; print(torch.cuda.is_available())"

📝 Logging

• Structured Logging: JSON format for all services
• Log Levels: Configurable via LOG_LEVEL environment variable
• Centralized: All logs stored in /data/logs/
• Monitoring: Real-time log viewing via dashboard

🔐 Security

• Environment Variables: Secure credential management
• Database: PostgreSQL with connection encryption
• Network: Internal Docker network isolation
• API Keys: Separate service credentials

🚀 Deployment

Unraid Setup

1. Install Community Applications plugin
2. Add Docker Compose plugin
3. Configure GPU passthrough
4. Import docker-compose.yml

Production Considerations

• SSL: Configure Nginx reverse proxy with SSL certificates
• Backup: Regular database and configuration backups
• Monitoring: Set up health check alerts
• Scaling: Horizontal scaling for high-traffic Discord servers

🛠️ Troubleshooting

Common Issues

GPU Not Detected

# Check NVIDIA drivers
nvidia-smi

# Verify Docker GPU support
docker run --rm --gpus all nvidia/cuda:11.8-base nvidia-smi

Service Won't Start

# Check logs
docker-compose logs [service-name]

# Verify environment variables
docker-compose config

Audio Processing Slow

• Verify GPU acceleration is working
• Check available VRAM
• Monitor CPU usage during conversion

📚 API Documentation

Once running, visit:

• Whisper API: http://localhost:8001/docs
• Translator API: http://localhost:8002/docs
• Dashboard: http://localhost:3000

🤝 Contributing

1. Fork the repository
2. Create feature branch: git checkout -b feature/amazing-feature
3. Commit changes: git commit -m 'Add amazing feature'
4. Push to branch: git push origin feature/amazing-feature
5. Open a Pull Request

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🎯 Roadmap

• Complete Translator service implementation
• Build Transcriber orchestration service
• Create web dashboard with real-time updates
• Add voice cloning capabilities
• Implement speaker diarization
• Support for additional languages
• Mobile app for remote monitoring
• Advanced analytics and insights

💡 Credits

Built with:

• faster-whisper for GPU-accelerated transcription
• Discord.js for Discord bot functionality
• FastAPI for high-performance APIs
• PostgreSQL for reliable data storage
• Redis for message queuing and caching

---

🚀 Ready to translate your Discord conversations in real-time with the power of your RTX 4000!