Voice AI chatbot with OpenAI, RAG (Qdrant) & Guardrails for WordPress

This workflow implements a complete Voice AI Chatbot system for Wordress that integrates speech recognition, guardrails for safety, retrieval-augmented generation (RAG), Qdrant vector search, and audio responses. It is designed to be connected to a WordPress Voicebot AI plugin through a webhook endpoint.

---

Key Advantages

✅ Complete Voice AI Pipeline The workflow handles: audio input STT intelligent processing TTS output All within a single automated process.

✅ Safe and Policy-Compliant Thanks to the Guardrails module, the system automatically: detects harmful or disallowed requests blocks them responds safely This protects both the user and the business.

✅ Contextual and Memory-Based Conversations The Window Buffer Memory tied to unique session IDs enables: continuous conversation flow natural dialogue better understanding of context

✅ Company-Specific Knowledge via RAG By integrating Qdrant as a vector store, the system can: retrieve business documentation give accurate and up-to-date answers support personalized content This makes the chatbot far more powerful than a standard LLM.

✅ Modular and Extensible Architecture Because everything is modular inside n8n, you can: swap OpenAI with other models add new tools or knowledge sources change prompts or capabilities without redesigning the entire workflow.