Voice RAG Chatbot with ElevenLabs and OpenAI

STEP 4 RAG System Click on "test workflow" on n8n and "Test AI agent" on ElevenLabs. If everything is configured correctly, when you ask a question to the agent, the webhook on n8n is activated with the "question" field in the body filled with the question asked to the voice agent. The AI ​​Agent will extract the information from the vector database, send it to the model to create the response which will be sent via the response webhook to ElevenLabs which will transform it into voice

Workflow Structure (18 nodes)
100%
Manual Trigger
When clicking ‘Test workflow’
Http Request
Create collection
Http Request
Refresh collection
Google Drive
Get folder
Google Drive
Download Files
Langchain.embeddings Open Ai
Embeddings OpenAI1
Langchain.vector Store Qdrant
Qdrant Vector Store1
Langchain.text Splitter Token Splitter
Token Splitter
Langchain.document Default Data Loader
Default Data Loader
Webhook
Listen
Langchain.lm Chat Open Ai
OpenAI
Langchain.agent
AI Agent
Langchain.vector Store Qdrant
Qdrant Vector Store
Langchain.embeddings Open Ai
Embeddings OpenAI
Langchain.memory Buffer Window
Window Buffer Memory
Langchain.tool Vector Store
Vector Store Tool
Langchain.lm Chat Open Ai
OpenAI Chat Model
Respond To Webhook
Respond to ElevenLabs
Node Types:
default
trigger
http
action
logic
Requires credentials

Prerequisites

Required Credentials (4)

Google Drive

Used by: Get folder, Download Files

Docs

HTTP Header Auth

Used by: Create collection, Refresh collection

Docs

OpenAI

Used by: Embeddings OpenAI, Embeddings OpenAI1 +2 more

Docs

Qdrant

Used by: Qdrant Vector Store, Qdrant Vector Store1

Docs

Multiple services required

This workflow needs 4 different credentials. Make sure you have accounts for all services before importing.

Complexity

Complex

Advanced features used. Requires n8n experience.

Setup time: ~45 min
Score: 60/100
5 Integrations

When to Use This Workflow

AI-Powered Content Creation

Automate content generation, summarization, or analysis using AI capabilities.

Save hours of manual work while maintaining quality and consistency.

Real-time Response

React instantly when events happen - new orders, form submissions, or API calls.

Zero delay between trigger and action for time-sensitive workflows.

Error Reduction

Eliminate human error from routine processes with consistent automation.

Improve accuracy and reliability across your workflows.

workflow.json
{
  "id": "ibiHg6umCqvcTF4g",
  "meta": {
    "instanceId": "a4bfc93e975ca233ac45ed7c9227d84cf5a2329310525917adaf3312e10d5462",
    "templateCredsSetupCompleted": true
  },
  "name": "Voice RAG Chatbot with ElevenLabs and OpenAI",
  "tags": [],
  "nodes": [
    {
      "id": "5898da57-38b0-4d29-af25-fe029cda7c4a",
      "name": "AI Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        -180,
        800
      ],
      "parameters": {
        "text": "={{ $json.body.question }}",
        "options": {},
...

Workflow Details

Nodes
23
Trigger
Webhook
Source
awesome
Added
Dec 4, 2025

Need Help?

Check out the official n8n documentation for detailed guides.

Related Workflows

OpenAI Personal Shopper with RAG and WooCommerce

Replace the URL and Collection name with your own

Chat
Memorybufferwindow
Toolcalculator
Lmchatopenai
25 nodesEvent
Curated

Business WhatsApp AI RAG Chatbot

STEP 4 RAG System Respond webhook receives various POST Requests from Meta regarding WhatsApp messages (user messages...

Agent
Lmchatopenai
Vectorstoreqdrant
Http-request
24 nodesWebhook
Curated

Building RAG Chatbot for Movie Recommendations with Qdrant and Open AI

Tool, calling Qdrant's recommendation API based on user's request, transformed by AI agent

Github
Embeddingsopenai
Documentdefaultdataloader
Textsplittertokensplitter
27 nodesEvent
Curated

Email AI Auto-responder. Summerize and send email

STEP 1 Create Qdrant Collection Change: - QDRANTURL - COLLECTION

Emailreadimap
Lmchatopenai
Emailsend
Vectorstoreqdrant
26 nodesManual
Curated

Chat with GitHub OpenAPI Specification using RAG (Pinecone and OpenAI)

Indexing content in the vector database This part of the workflow is responsible for extracting content, generating embe...

Http-request
Vectorstorepinecone
Documentdefaultdataloader
Textsplitterrecursivecharactertextsplitter
17 nodesEvent
Curated

Advanced AI Demo (Presented at AI Developers #14 meetup)

![h](https://i.postimg.cc/9XLvL5dL/slide-sf-talk.pngfull-width)

Slack
Textsplitterrecursivecharactertextsplitter
Embeddingsopenai
Documentdefaultdataloader
39 nodesEvent
Curated