Intelligent Voice Interaction Platform - Giving AI a Real Voice

English | 中文

🌐 Live Demo

Experience LingEcho online: https://lingecho.com

LingEcho is an enterprise-grade intelligent voice interaction platform based on Go + React, providing a complete AI voice interaction solution. It integrates advanced speech recognition (ASR), text-to-speech (TTS), large language models (LLM), and real-time communication technologies, supporting real-time calls, voice cloning, knowledge base management, workflow automation, device management, alerting, billing, and other enterprise-level features.

• AI Character Real-time Calls - Real-time voice calls with AI characters based on WebRTC technology, supporting high-quality audio transmission and low-latency interaction
• Voice Cloning & Training - Support for custom voice training and cloning, allowing AI assistants to have exclusive voice characteristics for personalized voice experiences
• Workflow Automation - Visual workflow designer with multiple trigger types (API, Event, Schedule, Webhook, Assistant), supporting complex business process automation
• Knowledge Base Management - Powerful knowledge base management system supporting document storage, retrieval, and AI analysis, providing intelligent knowledge services
• Application Integration - Quick integration of new applications through JS injection, API gateway, and key management, enabling seamless integration
• Device Management - Complete device management system with OTA firmware updates, device monitoring, and remote control
• Alert System - Comprehensive alerting system with rule-based monitoring, multi-channel notifications, and alert management
• Billing System - Flexible billing and usage tracking system with detailed usage records, bill generation, and quota management
• Organization Management - Multi-tenant organization management with group collaboration, member management, and resource sharing
• Key Management & API Platform - Enterprise-level key management system and API development platform
• VAD Voice Activity Detection - Standalone SileroVAD service supporting PCM and OPUS formats
• ️ Voiceprint Recognition Service - ModelScope-based voiceprint recognition service supporting speaker identification
• ASR-TTS Service - Standalone ASR (Whisper) and TTS (edge-tts) service supporting speech recognition and text-to-speech synthesis
• MCP Service - Model Context Protocol service supporting SSE and stdio transports
• Hardware Device Support - Support for xiaozhi protocol hardware devices with complete WebSocket communication

Visual workflow designer with drag-and-drop interface

Voice cloning and training interface

AI assistant debugging and testing interface

JavaScript template for application integration

For detailed architecture documentation, see Architecture Documentation.

• Go >= 1.24.0
• Node.js >= 18.0.0
• npm >= 8.0.0 or pnpm >= 8.0.0
• Git
• Python >= 3.10 (for optional services: VAD, Voiceprint, ASR-TTS)
• Docker & Docker Compose (for containerized deployment, recommended)

The easiest way to get started with LingEcho is using Docker Compose:

docker run -d --name neo4j \
  -p 7474:7474 -p 7687:7687 \
  -e NEO4J_AUTH=neo4j/admin123 \
  neo4j:latest
# Clone the project
git clone https://github.com/your-username/LingEcho.git
cd LingEcho

# Copy environment configuration
cp server/env.example .env

# Edit .env file and configure your settings
# At minimum, set: SESSION_SECRET, LLM_API_KEY

# Start services with Docker Compose
docker-compose up -d

# View logs
docker-compose logs -f lingecho

Access the Application:

• Frontend Interface: http://localhost:7072
• Backend API: http://localhost:7072/api
• API Documentation: http://localhost:7072/api/docs

Optional Services:

# Start with PostgreSQL database
docker-compose --profile postgres up -d

# Start with Redis cache
docker-compose --profile redis up -d

# Start with Nginx reverse proxy
docker-compose --profile nginx up -d

# Start frontend development server
docker-compose --profile dev up -d

brew install pkg-config
brew install opus opusfile

# Clone the project
git clone https://github.com/your-username/LingEcho.git
cd LingEcho

# Backend setup
cd server
go mod tidy
cp env.example .env
# Edit .env file with your configuration

# Frontend setup
cd ../web
npm install  # or pnpm install
npm run build  # For production
# OR
npm run dev    # For development (runs on port 5173)

# Start backend (from server directory)
cd ../server
go run ./cmd/server/main.go -mode=dev

Access the Application:

• Frontend Interface: http://localhost:5173 (dev) or http://localhost:7072 (production)
• Backend API: http://localhost:7072/api
• API Documentation: http://localhost:7072/api/docs

Optional Services (if needed):

# Start VAD service
cd services/vad-service
docker-compose up -d
# Or manually: python vad_service.py

# Start Voiceprint service
cd services/voiceprint-api
docker-compose up -d
# Or manually: python -m app.main

# Start ASR-TTS service
cd services/asr-tts-service
docker-compose up -d
# Or manually: python -m app.main

# Start MCP service (optional)
cd server
go run ./cmd/mcp/main.go --transport sse --port 3001

For detailed installation instructions, see Installation Guide.

• Installation Guide - Detailed installation and configuration instructions
• Features Documentation - Complete feature list with screenshots and examples
• Architecture Documentation - System architecture and design
• Development Guide - Development setup and contribution guidelines
• Services Documentation - Detailed service component documentation

We welcome all forms of contributions! Please check our Development Guide for details.

1. Fork the Project - Click the Fork button in the top right corner
2. Create a Branch - git checkout -b feature/your-feature
3. Commit Changes - git commit -m 'Add some feature'
4. Push Branch - git push origin feature/your-feature
5. Create PR - Create a Pull Request on GitHub

A core team of four full-stack engineers focused on innovation and application of AI voice technology.

• Email: 19511899044@163.com