Automate sales cold calling pipeline with Apify, GPT-4o, and WhatsApp
This workflow contains community nodes that are only compatible with the self-hosted version of n8n.
Cold Calling Automation - End-to-End Automated Cold Calling with Apify, RAG, and WhatsApp
The "Cold Calling Automation" workflow is designed to fully automate the end-to-end cold calling process by intelligently combining web scraping, AI-powered research, and WhatsApp messaging. Leveraging key technologies such as Apify for data scraping, RAG (Retrieval-Augmented Generation) for intelligent content creation, and WhatsApp integration for automated outreach, this workflow transforms raw prospect data into personalized, high-converting cold calling campaigns with minimal manual intervention.
💡 Why Use Cold Calling Automation?
- Scale Your Outreach: Automate hundreds of personalized cold calls without manual effort or hiring additional staff.
- Intelligent Personalization: RAG technology creates highly relevant, personalized messages based on prospect research.
- Multi-Channel Approach: Seamlessly integrate WhatsApp messaging with traditional cold calling methods.
- Real-Time Optimization: Continuously improve message performance and conversion rates through AI analysis.
- Cost-Effective: Reduce cold calling costs while dramatically increasing reach and response rates.
⚡ Who Is This For?
- Sales Teams: Looking to scale their cold calling efforts with intelligent automation and personalization.
- Lead Generation Agencies: Needing to deliver high-volume, high-quality cold calling services to clients.
- Business Development Professionals: Seeking to maximize outreach efficiency while maintaining personal touch.
- Small Business Owners: Who want professional-grade cold calling capabilities without hiring expensive sales teams.
- Marketing Agencies: Offering comprehensive lead generation and conversion services to clients.
❓ What Problem Does It Solve?
Traditional cold calling is time-consuming, expensive, and often ineffective due to lack of personalization and poor timing. Manual prospect research, script writing, and call execution create bottlenecks that limit outreach scale. Generic messages result in low response rates and damaged brand reputation. This workflow solves these problems by automating the entire cold calling pipeline - from prospect identification and research to personalized message creation and delivery - while maintaining high quality and relevance that converts prospects into qualified leads.
🔧 What This Workflow Does
⏱ Prospect Scraping: Uses Apify to automatically scrape and identify high-quality prospects based on your target criteria.
🔍 Intelligent Research: Employs RAG technology to research each prospect and gather relevant business intelligence.
✍️ Personalized Content: Automatically generates custom messages, scripts, and talking points for each prospect.
📱 WhatsApp Integration: Delivers personalized messages through WhatsApp automation for maximum engagement.
📊 Performance Tracking: Monitors response rates, engagement metrics, and conversion data for continuous optimization.
🤖 AI-Powered Follow-up: Automatically handles initial responses and schedules appropriate follow-up actions.
📈 Campaign Analytics: Provides detailed insights on campaign performance and ROI metrics.
🔄 Continuous Learning: Improves message effectiveness and targeting based on campaign results.
This workflow also using community node: @devlikeapro/n8n-nodes-waha
🔐 Setup Instructions
- Import the provided workflow JSON into your n8n instance (Cloud or self-hosted).
- Set up credentials:
- Apify API credentials for prospect scraping
- OpenAI API key for RAG and content generation
- WhatsApp Business API credentials or WAHA integration
- Database credentials for prospect and campaign tracking
- Email credentials for notifications and reporting
- Customize parameters:
- Target prospect criteria and scraping parameters
- Message templates and personalization rules
- Campaign timing and frequency settings
- Response handling and follow-up logic
- Performance tracking and reporting preferences
- Test the complete workflow with a small prospect list to verify scraping, personalization, and delivery.
🧩 Pre-Requirements
- Active n8n instance (Cloud or Self-hosted)
- Apify account with appropriate scraping credits
- OpenAI API key with sufficient usage limits
- WhatsApp Business account or WAHA setup
- Database system for prospect and campaign management
- Basic understanding of your target audience and value proposition
🛠️ Customize It Further
- Integrate with CRM systems to sync prospects and track conversion through sales pipeline.
- Add voice calling capabilities using VoIP services for complete omnichannel outreach.
- Implement A/B testing for message templates and timing optimization.
- Connect with social media platforms for multi-channel prospecting and engagement.
- Add sentiment analysis to optimize message tone and approach for different prospect types.
- Integrate with calendar systems for automatic meeting scheduling from qualified responses.
🧠 Nodes Used
- Apify nodes for prospect scraping and data collection
- OpenAI Chat Model and Embeddings for RAG implementation
- WhatsApp/WAHA nodes for message delivery and response handling
- Database nodes for prospect storage and campaign tracking
- HTTP Request nodes for API integrations and webhooks
- Code nodes for data processing and personalization logic
- Schedule Trigger for automated campaign execution
- Conditional nodes for response handling and follow-up logic
- Set nodes for parameter configuration and data transformation
- Split In Batches for efficient bulk processing
📊 Expected Results
- 50-80% increase in cold calling efficiency and prospect reach
- 25-40% higher response rates compared to generic cold calling
- 60-75% reduction in manual research and message preparation time
- Real-time insights into campaign performance and prospect engagement
- Scalable system that grows with your business needs
📞 Support
Made by: khaisa Studio
Tag: automation, cold calling, lead generation, apify, RAG, whatsapp, AI, sales automation, outreach
Category: Sales Automation & Lead Generation
Need a custom? contact me for more tailored templates
Automate Sales Cold Calling Pipeline with Apify, GPT-4o, and WhatsApp
This n8n workflow automates the process of generating sales leads, enriching them with AI, and initiating cold outreach via WhatsApp. It streamlines the initial stages of a sales pipeline by leveraging Apify for data extraction, OpenAI's GPT-4o for lead qualification and message generation, and WhatsApp for communication, with data managed in Google Sheets and Google Drive.
What it does:
- Triggers on new Google Sheet rows or manually: The workflow can be initiated either when a new row is added to a specified Google Sheet (e.g., a list of target companies) or manually for ad-hoc execution.
- Fetches company data from Google Sheets: It reads company names or other relevant data from a Google Sheet, which serves as the input for lead generation.
- Loops through each company: For each company identified, the workflow processes it individually.
- Extracts lead information using Apify: It uses an HTTP Request node to interact with the Apify API, likely to scrape company websites or public directories for contact details and other relevant information.
- Enriches data and generates outreach messages with AI (GPT-4o):
- Loads extracted data: The
Default Data Loaderprepares the data for AI processing. - Splits text for processing: The
Recursive Character Text Splitterbreaks down large text blocks into manageable chunks for the AI model. - Creates embeddings:
Embeddings OpenAIconverts the text into numerical vectors, enabling semantic search and understanding. - Stores in Supabase Vector Store: The embeddings are stored in a Supabase Vector Store for efficient retrieval.
- Utilizes an AI Agent with OpenAI Chat Model: An
AI Agent(likely powered by GPT-4o) interacts with theSupabase Vector StoreandPostgres Chat Memoryto:- Qualify leads based on predefined criteria.
- Generate personalized cold calling scripts or WhatsApp messages.
- Potentially identify key decision-makers or pain points.
- Reranks results with Cohere (optional): The
Reranker Coherenode can be used to improve the relevance of retrieved information before generating the final output.
- Loads extracted data: The
- Prepares data for WhatsApp outreach: The
Edit Fields (Set)node formats the AI-generated messages and lead details for sending via WhatsApp. - Sends personalized WhatsApp messages: An HTTP Request node (configured for a WhatsApp API, e.g., Twilio, MessageBird, or a custom integration) sends the tailored messages to the identified leads.
- Stores generated content or lead data in Google Drive: The
Google Drivenode saves the AI-generated messages, lead profiles, or other relevant outputs for record-keeping and future reference.
Prerequisites/Requirements:
- n8n Instance: A running n8n instance (cloud or self-hosted).
- Google Account: With access to Google Sheets and Google Drive.
- Google Sheets Credentials: Configured in n8n for reading input data.
- Google Drive Credentials: Configured in n8n for storing output.
- Apify Account and API Key: For web scraping and data extraction.
- OpenAI API Key: For the
Embeddings OpenAIandOpenAI Chat Modelnodes (GPT-4o or other compatible models). - Supabase Account: For the
Supabase Vector Store. - PostgreSQL Database: For the
Postgres Chat Memory(can be hosted on Supabase or separately). - WhatsApp Business API or similar integration: An API endpoint and credentials for sending WhatsApp messages (e.g., Twilio, MessageBird, or a custom solution that can be called via HTTP Request).
Setup/Usage:
- Import the workflow: Download the JSON provided and import it into your n8n instance.
- Configure Credentials:
- Set up your Google Sheets and Google Drive OAuth2 credentials.
- Add your Apify API Key as a header or query parameter in the
HTTP Requestnode (Node 19). - Configure your OpenAI API Key for the
Embeddings OpenAIandOpenAI Chat Modelnodes. - Set up Supabase and Postgres Chat Memory credentials (database URL, API keys, etc.).
- Configure the WhatsApp API
HTTP Requestnode (Node 19, or a new one if it's a separate step) with your chosen WhatsApp provider's API endpoint and authentication.
- Customize Google Sheets Trigger (Node 841):
- Specify the Spreadsheet ID and Sheet Name from which to read company data.
- Configure the trigger to listen for new rows.
- Customize Apify HTTP Request (Node 19):
- Update the URL and body to call your specific Apify actor for lead data extraction.
- Map the input from Google Sheets (e.g., company name) to the Apify request.
- Configure AI Agent (Node 1119) and related nodes:
- Review and adjust the prompts for the
OpenAI Chat Modelto define lead qualification criteria and desired WhatsApp message structure. - Ensure the
Supabase Vector StoreandPostgres Chat Memoryare correctly connected and configured with your database details. - Adjust
Recursive Character Text Splitterparameters if needed.
- Review and adjust the prompts for the
- Customize Edit Fields (Set) (Node 38):
- Map the AI-generated output (e.g., personalized message, contact number) to the fields required for the WhatsApp message.
- Configure WhatsApp HTTP Request (Node 19, if used for WhatsApp):
- Update the URL, headers, and body to match your WhatsApp API provider's requirements.
- Map the
phone_numberandmessage_contentfrom previous nodes.
- Customize Google Drive (Node 58):
- Specify the folder where generated files or lead data should be stored.
- Map the content to be saved from the preceding nodes.
- Activate the workflow: Once configured, activate the workflow to start automating your sales cold calling pipeline.
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.
By Ranjan DailataGenerate 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
By Daniel NkenchoAutomate 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.
By Le Nguyen