HumationHuman + Automation
Back to Catalog

Voice-driven AI assistant using VAPI and GPT-4.1-mini with memory

Robert BreenRobert Breen
699 views
2/3/2026
WebhookEvent ManagementAutomationData StorageGoogle Calendar
Official Page

Send VAPI voice requests into n8n with memory and OpenAI for conversational automation

This template shows how to capture voice interactions from VAPI (Voice AI Platform), send them into n8n via a webhook, process them with OpenAI, and maintain context with memory. The result is a conversational AI agent that responds back to VAPI with short, business-focused answers.

✅ What this template does

  • Listens for POST requests from VAPI containing the session ID and user query
  • Extracts session ID and query for consistent conversation context
  • Uses OpenAI (GPT-4.1-mini) to generate conversational replies
  • Adds Memory Buffer Window so each VAPI session maintains history
  • Returns results to VAPI in the correct JSON response format

👤 Who’s it for

  • Developers and consultants building voice-driven assistants
  • Businesses wanting to connect VAPI calls into automation workflows
  • Anyone who needs a scalable voice → AI → automation pipeline

⚙️ How it works

  1. Webhook node catches incoming VAPI requests
  2. Set node extracts session_id and user_query from the request body
  3. OpenAI Agent generates short, conversational replies with your business context
  4. Memory node keeps conversation history across turns
  5. Respond to Webhook sends results back to VAPI in the required JSON schema

🔧 Setup instructions

Step 1: Create Function Tool in VAPI

  1. In your VAPI dashboard, create a new Function Tool
    • Name: send_to_n8n
    • Description: Send user query and session data to n8n workflow
    • Parameters:
      • session_id (string, required) – Unique session identifier
      • user_query (string, required) – The user’s question
    • Server URL: https://your-n8n-instance.com/webhook/vapi-endpoint

Step 2: Configure Webhook in n8n

  1. Add a Webhook node
  2. Set HTTP method to POST
  3. Path: /webhook/vapi-endpoint
  4. Save, activate, and copy the webhook URL
  5. Use this URL in your VAPI Function Tool configuration

Step 3: Create VAPI Assistant

  1. In VAPI, create a new Assistant
  2. Add the send_to_n8n Function Tool
  3. Configure the assistant to call this tool on user requests
  4. Test by making a voice query — you should see n8n respond

📦 Requirements

  • An OpenAI API key stored in n8n credentials
  • A VAPI account with access to Function Tools
  • A self-hosted or cloud n8n instance with webhook access

🎛 Customization

  • Update the system prompt in the OpenAI Agent node to reflect your brand’s voice
  • Swap GPT-4.1-mini for another OpenAI model if you need longer or cheaper responses
  • Extend the workflow by connecting to CRMs, Slack, or databases

📬 Contact

Need help customizing this (e.g., filtering by campaign, connecting to CRMs, or formatting reports)?

  • 📧 rbreen@ynteractive.com
  • 🔗 https://www.linkedin.com/in/robert-breen-29429625/
  • 🌐 https://ynteractive.com

Voice-Driven AI Assistant using Vapi and GPT-4.1 Mini with Memory

This n8n workflow demonstrates how to build a voice-driven AI assistant that leverages Vapi for real-time voice interaction, an OpenAI Chat Model (likely GPT-4.1 Mini based on the directory name hint) for conversational AI, and a simple memory buffer to maintain context.

The workflow acts as a backend for a voice assistant, receiving user input via a webhook, processing it with an AI agent, and responding with a generated message. The "Simple Memory" node ensures that the AI agent can remember previous turns in the conversation, leading to more coherent and natural interactions.

What it does

  1. Listens for Voice Input: Initiates when a Webhook receives an incoming request, typically from a voice interaction platform like Vapi, containing user's spoken input.
  2. Sets Initial Data: An Edit Fields (Set) node is present, though its specific configuration isn't detailed in the JSON, it's typically used to structure or transform the incoming webhook data for subsequent nodes.
  3. Maintains Conversation Context: A Simple Memory node (likely a Buffer Window Memory) stores previous parts of the conversation, allowing the AI to recall past interactions.
  4. Processes with AI Agent: An AI Agent node (from LangChain) orchestrates the interaction with the language model, using the provided memory to generate intelligent responses.
  5. Generates AI Response: An OpenAI Chat Model node (from LangChain) is the core language model, taking the user's input and conversational history to generate a relevant and natural language response.
  6. Responds to Voice Platform: The Respond to Webhook node sends the AI-generated response back to the initiating voice platform (e.g., Vapi) to be spoken back to the user.

Prerequisites/Requirements

  • n8n Instance: A running n8n instance (self-hosted or cloud).
  • OpenAI API Key: An API key for OpenAI to use their chat models (e.g., GPT-4.1 Mini). This will need to be configured as a credential in n8n for the OpenAI Chat Model node.
  • Vapi Account (or similar voice platform): A voice API platform that can send webhook requests and receive responses. The webhook URL from this n8n workflow will need to be configured in your Vapi assistant.
  • LangChain Nodes: Ensure the @n8n/n8n-nodes-langchain package is installed in your n8n instance.

Setup/Usage

  1. Import the Workflow: Import the provided JSON into your n8n instance.
  2. Configure Webhook:
    • Activate the Webhook node.
    • Copy the "Webhook URL" provided by the node.
    • Paste this URL into your Vapi assistant configuration (or whichever voice platform you are using) as the endpoint for handling user input.
  3. Configure OpenAI Credentials:
    • Click on the OpenAI Chat Model node.
    • Select or create a new "OpenAI API" credential.
    • Enter your OpenAI API Key.
  4. Configure AI Agent and Memory:
    • Review the AI Agent and Simple Memory nodes to ensure their configurations (e.g., model name, memory window size) meet your requirements. The OpenAI Chat Model will likely be set to a model like gpt-4-1106-preview or gpt-3.5-turbo by default, but you can adjust it.
  5. Activate the Workflow: Save and activate the workflow.

Once activated, your voice assistant should be ready to receive voice input via Vapi (or your chosen platform), process it with the AI, and respond in real-time.

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 Dutch Public Procurement Data Collection with TenderNed

TenderNed Public Procurement What This Workflow Does This workflow automates the collection of public procurement data from TenderNed (the official Dutch tender platform). It: Fetches the latest tender publications from the TenderNed API Retrieves detailed information in both XML and JSON formats for each tender Parses and extracts key information like organization names, titles, descriptions, and reference numbers Filters results based on your custom criteria Stores the data in a database for easy querying and analysis Setup Instructions This template comes with sticky notes providing step-by-step instructions in Dutch and various query options you can customize. Prerequisites TenderNed API Access - Register at TenderNed for API credentials Configuration Steps Set up TenderNed credentials: Add HTTP Basic Auth credentials with your TenderNed API username and password Apply these credentials to the three HTTP Request nodes: "Tenderned Publicaties" "Haal XML Details" "Haal JSON Details" Customize filters: Modify the "Filter op ..." node to match your specific requirements Examples: specific organizations, contract values, regions, etc. How It Works Step 1: Trigger The workflow can be triggered either manually for testing or automatically on a daily schedule. Step 2: Fetch Publications Makes an API call to TenderNed to retrieve a list of recent publications (up to 100 per request). Step 3: Process & Split Extracts the tender array from the response and splits it into individual items for processing. Step 4: Fetch Details For each tender, the workflow makes two parallel API calls: XML endpoint - Retrieves the complete tender documentation in XML format JSON endpoint - Fetches metadata including reference numbers and keywords Step 5: Parse & Merge Parses the XML data and merges it with the JSON metadata and batch information into a single data structure. Step 6: Extract Fields Maps the raw API data to clean, structured fields including: Publication ID and date Organization name Tender title and description Reference numbers (kenmerk, TED number) Step 7: Filter Applies your custom filter criteria to focus on relevant tenders only. Step 8: Store Inserts the processed data into your database for storage and future analysis. Customization Tips Modify API Parameters In the "Tenderned Publicaties" node, you can adjust: offset: Starting position for pagination size: Number of results per request (max 100) Add query parameters for date ranges, status filters, etc. Add More Fields Extend the "Splits Alle Velden" node to extract additional fields from the XML/JSON data, such as: Contract value estimates Deadline dates CPV codes (procurement classification) Contact information Integrate Notifications Add a Slack, Email, or Discord node after the filter to get notified about new matching tenders. Incremental Updates Modify the workflow to only fetch new tenders by: Storing the last execution timestamp Adding date filters to the API query Only processing publications newer than the last run Troubleshooting No data returned? Verify your TenderNed API credentials are correct Check that you have setup youre filter proper Need help setting this up or interested in a complete tender analysis solution? Get in touch 🔗 LinkedIn – Wessel Bulte

Wessel BulteBy Wessel Bulte
247