SoulNexus is an enterprise-grade intelligent voice interaction platform designed to provide a comprehensive AI voice solution. It targets businesses seeking to integrate advanced voice capabilities, offering real-time AI-powered communication, custom voice experiences, and automated workflows, thereby enhancing customer engagement and operational efficiency.

How It Works

Built with Go for the backend and React/TypeScript for the frontend, SoulNexus integrates core AI technologies including Automatic Speech Recognition (ASR), Text-to-Speech (TTS), Large Language Models (LLMs), and real-time communication via WebRTC. Its architecture features a microservices approach, with dedicated services for Voice Activity Detection (VAD), Voiceprint Recognition, and ASR/TTS. A key component is its visual workflow designer, enabling the automation of complex business processes through a drag-and-drop interface.

Quick Start & Requirements

• Primary install / run command: Docker Compose (docker-compose up -d) is recommended for ease of setup. Manual installation involves backend setup (go mod tidy, go run ./cmd/server/main.go) and frontend setup (npm install, npm run build or npm run dev).
• Non-default prerequisites: Go >= 1.24.0, Node.js >= 18.0.0, npm >= 8.0.0 or pnpm >= 8.0.0, Git. Python >= 3.10 is required for optional VAD, Voiceprint, and ASR-TTS services. Docker & Docker Compose are recommended