HumationHuman + Automation
Back to Catalog

AI voice chatbot with ElevenLabs & OpenAI for customer service and restaurants

DavideDavide
65772 views
2/3/2026
ChecklistTrelloAutomationProject ManagementProductivity
Official Page

The "Voice RAG Chatbot with ElevenLabs and OpenAI" workflow in n8n is designed to create an interactive voice-based chatbot system that leverages both text and voice inputs for providing information. Ideal for shops, commercial activities and restaurants

How it works:

Here's how it operates:

  1. Webhook Activation: The process begins when a user interacts with the voice agent set up on ElevenLabs, triggering a webhook in n8n. This webhook sends a question from the user to the AI Agent node.
  2. AI Agent Processing: Upon receiving the query, the AI Agent node processes the input using predefined prompts and tools. It extracts relevant information from the knowledge base stored within the Qdrant vector database.
  3. Knowledge Base Retrieval: The Vector Store Tool node interfaces with the Qdrant Vector Store to retrieve pertinent documents or data segments matching the user’s query.
  4. Text Generation: Using the retrieved information, the OpenAI Chat Model generates a coherent response tailored to the user’s question.
  5. Response Delivery: The generated response is sent back through another webhook to ElevenLabs, where it is converted into speech and delivered audibly to the user.
  6. Continuous Interaction: For ongoing conversations, the Window Buffer Memory ensures context retention by maintaining a history of interactions, enhancing the conversational flow.

Set up steps:

To configure this workflow effectively, follow these detailed setup instructions:

  1. ElevenLabs Agent Creation:

    • Create a FREE account on ElevenLabs
    • Begin by creating an agent on ElevenLabs (e.g., named 'test_n8n').
    • Customize the first message and define the system prompt specific to your use case, such as portraying a character like a waiter at "Pizzeria da Michele".
    • Add a Webhook tool labeled 'test_chatbot_elevenlabs' configured to receive questions via POST requests.

  2. Qdrant Collection Initialization:

    • Utilize the HTTP Request nodes ('Create collection' and 'Refresh collection') to initialize and clear existing collections in Qdrant. Ensure you update placeholders QDRANTURL and COLLECTION accordingly.

  3. Document Vectorization:

    • Use Google Drive integration to fetch documents from a designated folder. These documents are then downloaded and processed for embedding.
    • Employ the Embeddings OpenAI node to generate embeddings for the downloaded files before storing them into Qdrant via the Qdrant Vector Store node.

  4. AI Agent Configuration:

    • Define the system prompt for the AI Agent node which guides its behavior and responses based on the nature of queries expected (e.g., product details, troubleshooting tips).
    • Link necessary models and tools including OpenAI language models and memory buffers to enhance interaction quality.

  5. Testing Workflow:

    • Execute test runs of the entire workflow by clicking 'Test workflow' in n8n alongside initiating tests on the ElevenLabs side to confirm all components interact seamlessly.
    • Monitor logs and outputs closely during testing phases to ensure accurate data flow between systems.

  6. Integration with Website:

    • Finally, integrate the chatbot widget onto your business website replacing placeholder AGENT_ID with the actual identifier created earlier on ElevenLabs.

By adhering to these comprehensive guidelines, users can successfully deploy a sophisticated voice-driven chatbot capable of delivering precise answers utilizing advanced retrieval-augmented generation techniques powered by OpenAI and ElevenLabs technologies.

Need help customizing?

Contact me for consulting and support or add me on Linkedin.

AI Voice Chatbot with ElevenLabs & OpenAI for Customer Service and Restaurants

This n8n workflow creates a sophisticated AI chatbot that can answer questions using a knowledge base stored in Google Drive, powered by OpenAI and Qdrant. It's designed for scenarios like customer service, particularly useful for businesses such as restaurants to provide instant, voice-enabled information.

What it does

This workflow orchestrates several AI and data management components to deliver an intelligent chatbot:

  1. Receives Webhook Input: It starts by listening for incoming requests via a webhook, which would typically contain user queries.
  2. Initializes AI Agent: An AI Agent (LangChain) is set up to manage the conversational flow and decide which tools to use.
  3. Configures Conversational Memory: A simple memory buffer is used to maintain context throughout the conversation, allowing the chatbot to remember previous interactions.
  4. Connects to OpenAI Chat Model: The core of the chatbot's intelligence comes from an OpenAI Chat Model, which processes natural language and generates responses.
  5. Loads Documents from Google Drive: It fetches documents from a specified Google Drive folder, which serves as the knowledge base for the chatbot.
  6. Splits Documents into Tokens: The retrieved documents are processed by a Token Splitter to break them down into manageable chunks (tokens) suitable for embedding.
  7. Generates Embeddings with OpenAI: OpenAI Embeddings are created from these tokenized document chunks, converting text into numerical vectors.
  8. Stores Embeddings in Qdrant Vector Store: The generated embeddings are then stored in a Qdrant Vector Store, enabling efficient semantic search.
  9. Sets up Vector Store Question Answer Tool: A specialized tool is configured to query the Qdrant Vector Store, allowing the AI agent to retrieve relevant information from the knowledge base to answer user questions.
  10. Responds via Webhook: Finally, the AI Agent's generated response is sent back via the webhook, completing the interaction.

Prerequisites/Requirements

To use this workflow, you will need:

  • n8n Instance: A running instance of n8n.
  • OpenAI API Key: For the OpenAI Chat Model and Embeddings.
  • Google Drive Account: To store your knowledge base documents.
  • Qdrant Instance: A running Qdrant vector database (self-hosted or cloud) to store and retrieve document embeddings.
  • LangChain Nodes: Ensure the @n8n/n8n-nodes-langchain package is installed in your n8n instance.

Setup/Usage

  1. Import the Workflow: Download the JSON definition and import it into your n8n instance.
  2. Configure Credentials:
    • OpenAI: Set up your OpenAI API key credential for both the "OpenAI Chat Model" and "Embeddings OpenAI" nodes.
    • Google Drive: Configure your Google Drive credential for the "Google Drive" node.
    • Qdrant: Set up your Qdrant credential for the "Qdrant Vector Store" node, providing the host and API key if required.
  3. Configure Nodes:
    • Webhook: The "Webhook" node will provide a unique URL. This is the endpoint your voice chatbot application will send user queries to.
    • Google Drive: Specify the folder or files in Google Drive that contain your knowledge base documents (e.g., restaurant menus, FAQs, customer service policies).
    • Qdrant Vector Store: Ensure the collection name and other settings match your Qdrant setup.
    • AI Agent: Review the agent's prompt and ensure it aligns with your desired chatbot persona and objectives.
  4. Activate the Workflow: Once all credentials and nodes are configured, activate the workflow.
  5. Integrate with Voice Application: Connect this webhook endpoint to your voice chatbot application (e.g., an ElevenLabs-powered frontend) to send user speech-to-text queries and receive text responses.

Related Templates

Track competitor SEO keywords with Decodo + GPT-4.1-mini + Google Sheets

This workflow automates competitor keyword research using OpenAI LLM and Decodo for intelligent web scraping. Who this is for SEO specialists, content strategists, and growth marketers who want to automate keyword research and competitive intelligence. Marketing analysts managing multiple clients or websites who need consistent SEO tracking without manual data pulls. Agencies or automation engineers using Google Sheets as an SEO data dashboard for keyword monitoring and reporting. What problem this workflow solves Tracking competitor keywords manually is slow and inconsistent. Most SEO tools provide limited API access or lack contextual keyword analysis. This workflow solves that by: Automatically scraping any competitor’s webpage with Decodo. Using OpenAI GPT-4.1-mini to interpret keyword intent, density, and semantic focus. Storing structured keyword insights directly in Google Sheets for ongoing tracking and trend analysis. What this workflow does Trigger — Manually start the workflow or schedule it to run periodically. Input Setup — Define the website URL and target country (e.g., https://dev.to, france). Data Scraping (Decodo) — Fetch competitor web content and metadata. Keyword Analysis (OpenAI GPT-4.1-mini) Extract primary and secondary keywords. Identify focus topics and semantic entities. Generate a keyword density summary and SEO strength score. Recommend optimization and internal linking opportunities. Data Structuring — Clean and convert GPT output into JSON format. Data Storage (Google Sheets) — Append structured keyword data to a Google Sheet for long-term tracking. Setup Prerequisites If you are new to Decode, please signup on this link visit.decodo.com n8n account with workflow editor access Decodo API credentials OpenAI API key Google Sheets account connected via OAuth2 Make sure to install the Decodo Community node. Create a Google Sheet Add columns for: primarykeywords, seostrengthscore, keyworddensity_summary, etc. Share with your n8n Google account. Connect Credentials Add credentials for: Decodo API credentials - You need to register, login and obtain the Basic Authentication Token via Decodo Dashboard OpenAI API (for GPT-4o-mini) Google Sheets OAuth2 Configure Input Fields Edit the “Set Input Fields” node to set your target site and region. Run the Workflow Click Execute Workflow in n8n. View structured results in your connected Google Sheet. How to customize this workflow Track Multiple Competitors → Use a Google Sheet or CSV list of URLs; loop through them using the Split In Batches node. Add Language Detection → Add a Gemini or GPT node before keyword analysis to detect content language and adjust prompts. Enhance the SEO Report → Expand the GPT prompt to include backlink insights, metadata optimization, or readability checks. Integrate Visualization → Connect your Google Sheet to Looker Studio for SEO performance dashboards. Schedule Auto-Runs → Use the Cron Node to run weekly or monthly for competitor keyword refreshes. Summary This workflow automates competitor keyword research using: Decodo for intelligent web scraping OpenAI GPT-4.1-mini for keyword and SEO analysis Google Sheets for live tracking and reporting It’s a complete AI-powered SEO intelligence pipeline ideal for teams that want actionable insights on keyword gaps, optimization opportunities, and content focus trends, without relying on expensive SEO SaaS tools.

Ranjan DailataBy Ranjan Dailata
161

Generate song lyrics and music from text prompts using OpenAI and Fal.ai Minimax

Spark your creativity instantly in any chat—turn a simple prompt like "heartbreak ballad" into original, full-length lyrics and a professional AI-generated music track, all without leaving your conversation. 📋 What This Template Does This chat-triggered workflow harnesses AI to generate detailed, genre-matched song lyrics (at least 600 characters) from user messages, then queues them for music synthesis via Fal.ai's minimax-music model. It polls asynchronously until the track is ready, delivering lyrics and audio URL back in chat. Crafts original, structured lyrics with verses, choruses, and bridges using OpenAI Submits to Fal.ai for melody, instrumentation, and vocals aligned to the style Handles long-running generations with smart looping and status checks Returns complete song package (lyrics + audio link) for seamless sharing 🔧 Prerequisites n8n account (self-hosted or cloud with chat integration enabled) OpenAI account with API access for GPT models Fal.ai account for AI music generation 🔑 Required Credentials OpenAI API Setup Go to platform.openai.com → API keys (sidebar) Click "Create new secret key" → Name it (e.g., "n8n Songwriter") Copy the key and add to n8n as "OpenAI API" credential type Test by sending a simple chat completion request Fal.ai HTTP Header Auth Setup Sign up at fal.ai → Dashboard → API Keys Generate a new API key → Copy it In n8n, create "HTTP Header Auth" credential: Name="Fal.ai", Header Name="Authorization", Header Value="Key [Your API Key]" Test with a simple GET to their queue endpoint (e.g., /status) ⚙️ Configuration Steps Import the workflow JSON into your n8n instance Assign OpenAI API credentials to the "OpenAI Chat Model" node Assign Fal.ai HTTP Header Auth to the "Generate Music Track", "Check Generation Status", and "Fetch Final Result" nodes Activate the workflow—chat trigger will appear in your n8n chat interface Test by messaging: "Create an upbeat pop song about road trips" 🎯 Use Cases Content Creators: YouTubers generating custom jingles for videos on the fly, streamlining production from idea to audio export Educators: Music teachers using chat prompts to create era-specific folk tunes for classroom discussions, fostering interactive learning Gift Personalization: Friends crafting anniversary R&B tracks from shared memories via quick chats, delivering emotional audio surprises Artist Brainstorming: Songwriters prototyping hip-hop beats in real-time during sessions, accelerating collaboration and iteration ⚠️ Troubleshooting Invalid JSON from AI Agent: Ensure the system prompt stresses valid JSON; test the agent standalone with a sample query Music Generation Fails (401/403): Verify Fal.ai API key has minimax-music access; check usage quotas in dashboard Status Polling Loops Indefinitely: Bump wait time to 45-60s for complex tracks; inspect fal.ai queue logs for bottlenecks Lyrics Under 600 Characters: Tweak agent prompt to enforce fuller structures like [V1][C][V2][B][C]; verify output length in executions

Daniel NkenchoBy Daniel Nkencho
601

Automate invoice processing with OCR, GPT-4 & Salesforce opportunity creation

PDF Invoice Extractor (AI) End-to-end pipeline: Watch Drive ➜ Download PDF ➜ OCR text ➜ AI normalize to JSON ➜ Upsert Buyer (Account) ➜ Create Opportunity ➜ Map Products ➜ Create OLI via Composite API ➜ Archive to OneDrive. --- Node by node (what it does & key setup) 1) Google Drive Trigger Purpose: Fire when a new file appears in a specific Google Drive folder. Key settings: Event: fileCreated Folder ID: google drive folder id Polling: everyMinute Creds: googleDriveOAuth2Api Output: Metadata { id, name, ... } for the new file. --- 2) Download File From Google Purpose: Get the file binary for processing and archiving. Key settings: Operation: download File ID: ={{ $json.id }} Creds: googleDriveOAuth2Api Output: Binary (default key: data) and original metadata. --- 3) Extract from File Purpose: Extract text from PDF (OCR as needed) for AI parsing. Key settings: Operation: pdf OCR: enable for scanned PDFs (in options) Output: JSON with OCR text at {{ $json.text }}. --- 4) Message a model (AI JSON Extractor) Purpose: Convert OCR text into strict normalized JSON array (invoice schema). Key settings: Node: @n8n/n8n-nodes-langchain.openAi Model: gpt-4.1 (or gpt-4.1-mini) Message role: system (the strict prompt; references {{ $json.text }}) jsonOutput: true Creds: openAiApi Output (per item): $.message.content → the parsed JSON (ensure it’s an array). --- 5) Create or update an account (Salesforce) Purpose: Upsert Buyer as Account using an external ID. Key settings: Resource: account Operation: upsert External Id Field: taxid_c External Id Value: ={{ $json.message.content.buyer.tax_id }} Name: ={{ $json.message.content.buyer.name }} Creds: salesforceOAuth2Api Output: Account record (captures Id) for downstream Opportunity. --- 6) Create an opportunity (Salesforce) Purpose: Create Opportunity linked to the Buyer (Account). Key settings: Resource: opportunity Name: ={{ $('Message a model').item.json.message.content.invoice.code }} Close Date: ={{ $('Message a model').item.json.message.content.invoice.issue_date }} Stage: Closed Won Amount: ={{ $('Message a model').item.json.message.content.summary.grand_total }} AccountId: ={{ $json.id }} (from Upsert Account output) Creds: salesforceOAuth2Api Output: Opportunity Id for OLI creation. --- 7) Build SOQL (Code / JS) Purpose: Collect unique product codes from AI JSON and build a SOQL query for PricebookEntry by Pricebook2Id. Key settings: pricebook2Id (hardcoded in script): e.g., 01sxxxxxxxxxxxxxxx Source lines: $('Message a model').first().json.message.content.products Output: { soql, codes } --- 8) Query PricebookEntries (Salesforce) Purpose: Fetch PricebookEntry.Id for each Product2.ProductCode. Key settings: Resource: search Query: ={{ $json.soql }} Creds: salesforceOAuth2Api Output: Items with Id, Product2.ProductCode (used for mapping). --- 9) Code in JavaScript (Build OLI payloads) Purpose: Join lines with PBE results and Opportunity Id ➜ build OpportunityLineItem payloads. Inputs: OpportunityId: ={{ $('Create an opportunity').first().json.id }} Lines: ={{ $('Message a model').first().json.message.content.products }} PBE rows: from previous node items Output: { body: { allOrNone:false, records:[{ OpportunityLineItem... }] } } Notes: Converts discount_total ➜ per-unit if needed (currently commented for standard pricing). Throws on missing PBE mapping or empty lines. --- 10) Create Opportunity Line Items (HTTP Request) Purpose: Bulk create OLIs via Salesforce Composite API. Key settings: Method: POST URL: https://<your-instance>.my.salesforce.com/services/data/v65.0/composite/sobjects Auth: salesforceOAuth2Api (predefined credential) Body (JSON): ={{ $json.body }} Output: Composite API results (per-record statuses). --- 11) Update File to One Drive Purpose: Archive the original PDF in OneDrive. Key settings: Operation: upload File Name: ={{ $json.name }} Parent Folder ID: onedrive folder id Binary Data: true (from the Download node) Creds: microsoftOneDriveOAuth2Api Output: Uploaded file metadata. --- Data flow (wiring) Google Drive Trigger → Download File From Google Download File From Google → Extract from File → Update File to One Drive Extract from File → Message a model Message a model → Create or update an account Create or update an account → Create an opportunity Create an opportunity → Build SOQL Build SOQL → Query PricebookEntries Query PricebookEntries → Code in JavaScript Code in JavaScript → Create Opportunity Line Items --- Quick setup checklist 🔐 Credentials: Connect Google Drive, OneDrive, Salesforce, OpenAI. 📂 IDs: Drive Folder ID (watch) OneDrive Parent Folder ID (archive) Salesforce Pricebook2Id (in the JS SOQL builder) 🧠 AI Prompt: Use the strict system prompt; jsonOutput = true. 🧾 Field mappings: Buyer tax id/name → Account upsert fields Invoice code/date/amount → Opportunity fields Product name must equal your Product2.ProductCode in SF. ✅ Test: Drop a sample PDF → verify: AI returns array JSON only Account/Opportunity created OLI records created PDF archived to OneDrive --- Notes & best practices If PDFs are scans, enable OCR in Extract from File. If AI returns non-JSON, keep “Return only a JSON array” as the last line of the prompt and keep jsonOutput enabled. Consider adding validation on parsing.warnings to gate Salesforce writes. For discounts/taxes in OLI: Standard OLI fields don’t support per-line discount amounts directly; model them in UnitPrice or custom fields. Replace the Composite API URL with your org’s domain or use the Salesforce node’s Bulk Upsert for simplicity.

Le NguyenBy Le Nguyen
942