This article provides a complete, practical walkthrough of the Webhook Manual Create Webhook n8n agent. It connects HTTP Request, Webhook across approximately 1 node(s). Expect a Intermediate setup in 15-45 minutes. One‑time purchase: €29.

What This Agent Does

This agent orchestrates a reliable automation between HTTP Request, Webhook, handling triggers, data enrichment, and delivery with guardrails for errors and rate limits.

It streamlines multi‑step processes that would otherwise require manual exports, spreadsheet cleanup, and repeated API requests. By centralizing logic in n8n, it reduces context switching, lowers error rates, and ensures consistent results across teams.

Typical outcomes include faster lead handoffs, automated notifications, accurate data synchronization, and better visibility via execution logs and optional Slack/Email alerts.

How It Works

The workflow uses standard n8n building blocks like Webhook or Schedule triggers, HTTP Request for API calls, and control nodes (IF, Merge, Set) to validate inputs, branch on conditions, and format outputs. Retries and timeouts improve resilience, while credentials keep secrets safe.

Third‑Party Integrations

• HTTP Request
• Webhook

Import and Use in n8n

1. Open n8n and create a new workflow or collection.
2. Choose Import from File or Paste JSON.
3. Paste the JSON below, then click Import.
4. Show n8n JSON

   Title:
   Turn Sales Calls into Actionable Insights: Automated Call Analysis With AssemblyAI, OpenAI, and Supabase using n8n
   
   Meta Description:
   Discover how to transcribe, analyze, and store sales call data using an automated n8n workflow. Leverage AssemblyAI for transcription, OpenAI for call analysis via GPT-4, and Supabase for structured data storage—an end-to-end solution for enhancing sales performance.
   
   Keywords:
   n8n sales workflow, call analysis workflow, AssemblyAI transcription, OpenAI GPT-4 sales analysis, call transcription automation, Supabase call data storage, AI sales call review, automated sales insight generator, sales performance analytics, speaker diarization, call center automation, conversational intelligence, sales intelligence tool
   
   Third-party APIs Used in the Workflow:
   
   1. AssemblyAI API
      - Purpose: Transcribes sales call audio and identifies speakers through diarization.
      - Endpoint(s): 
        - POST https://api.assemblyai.com/v2/transcript
        - GET https://api.assemblyai.com/v2/transcript/{transcript_id}
   
   2. OpenAI API
      - Purpose: Performs detailed analysis using GPT-4o, structured via a provided JSON schema to produce actionable insights from the call transcription.
      - Endpoint:
        - POST https://api.openai.com/v1/chat/completions
   
   3. Supabase API
      - Purpose: Stores both the raw transcription and structured analysis of the call in a database for future reference or integration into dashboards or CRM systems.
      - Endpoint: Custom Supabase client to insert a record into the "demo_calls" table
   
   Article:
   
   Revolutionize Sales Call Analysis with Automation: The Power of AssemblyAI, OpenAI, and Supabase in n8n
   
   In today's digitized, customer-centric world, follow-up calls are crucial checkpoints in the sales pipeline—but far too often, their insights are buried in audio files or forgotten outright. What if you could automatically convert call recordings into structured sales intelligence that empowers your team to close more deals? That's exactly what this low-code n8n workflow delivers.
   
   Designed by Mark Shcherbakov from the 5minAI community, this workflow seamlessly combines AssemblyAI, OpenAI, and Supabase to transcribe, analyze, and store sales calls—turning conversation into conversion-ready insights. Let's explore how this powerful automation unfolds.
   
   Step 1: Call Transcription with AssemblyAI  
   The journey begins with a manual trigger or webhook, used to kick off analysis once an audio file is available—either uploaded manually or collected via integrations.
   
   The workflow then passes the audio URL to AssemblyAI’s transcription engine through a POST request. Key features like speaker diarization (speaker_labels=true), expected speaker count, language setting, and a return webhook URL ensure the transcript is clean, accurate, and sent back to n8n for further processing.
   
   Features leveraged:
   - Audio URL-based asynchronous transcription
   - Speaker identification
   - Webhook callback for completed transcriptions
   
   Step 2: Webhook-Driven Automation  
   Once AssemblyAI finishes processing, it sends a POST request to the specified webhook in n8n. This webhook includes the status and a unique transcript_id.
   
   The workflow checks the status (e.g., "completed") using an If node and proceeds only when the transcription is ready. This ensures reliability and avoids premature processing.
   
   Step 3: Fetching the Full Transcript  
   Using the transcript_id from the webhook, the workflow makes a GET request to AssemblyAI’s API to retrieve the full transcript, including utterances separated by speaker. These utterances will be the foundation of the sales analysis.
   
   Step 4: AI-Powered Analysis by OpenAI  
   At this stage, the real magic kicks in. The utterances are transformed into a visual transcript (e.g., “Speaker A: Hello…”) and sent to OpenAI’s GPT-4o through the Chat Completions endpoint.
   
   Rather than returning raw, unstructured insights, OpenAI is provided with a detailed prompt and a custom JSON schema. This structure ensures consistent, measurable output. The evaluation covers:
   
   - Client Intent
   - Interest Score
   - Service Presentation Score
   - Upsell Opportunity Identified
   - Objection Handling Score
   - Conversion Probability
   - Outcome Summary
   - Client Needs
   - Agent Feedback
   - Recommended Next Steps
   
   In short, OpenAI transforms ordinary transcripts into actionable sales metrics.
   
   Step 5: Storing Analysis in Supabase  
   The final step involves saving both the input (transcription text, audio URL, transcript ID) and output (structured JSON from OpenAI) into a Supabase database (“demo_calls” table).
   
   This makes it easy to build front-end dashboards, CRM integration, or trigger follow-ups based on data, like a low Conversion Probability or unaddressed objections.
   
   Additional Features and Notes
   
   - Sticky notes embedded in the n8n canvas guide users on required variable replacements (e.g., API keys, audio URLs, prompt tweaks).
   - Optional direct integration with YouTube tutorials is available for fast onboarding.
   - JSON schema support ensures OpenAI output can be used for automated reporting, dashboards, and performance monitoring.
   
   Why This Matters  
   Sales calls are rich with customer intent, objections, and decision signals—but manual note-taking and post-call evaluations rarely capture them all. This workflow flips that dynamic: it ensures that every call is not only recorded but decoded and stored with intelligent insights.
   
   Whether you’re a sales team looking to improve conversion rates or a product team mapping feature interest trends, this automation offers a scalable, reliable, and intelligent solution.
   
   Ready to Supercharge Your Sales Calls?  
   With less than an hour of configuration, this no-code/low-code automation makes it possible to scale call intelligence across teams without ever hiring an analyst.
   
   Start by integrating your own call recordings and make sure to replace the placeholder API keys, webhook, and Supabase credentials. The only thing standing between your team and actionable insights is a single start node in n8n.
   
   Created by: Mark Shcherbakov  
   Powered by: The 5minAI Community  
   Watch the setup on YouTube: https://www.youtube.com/watch?v=kS41gut8l0g
   
   Let every call speak volumes—automatically.

5. Set credentials for each API node (keys, OAuth) in Credentials.
6. Run a test via Execute Workflow. Inspect Run Data, then adjust parameters.
7. Enable the workflow to run on schedule, webhook, or triggers as configured.

Tips: keep secrets in credentials, add retries and timeouts on HTTP nodes, implement error notifications, and paginate large API fetches.

Validation: use IF/Code nodes to sanitize inputs and guard against empty payloads.

Why Automate This with AI Agents

AI‑assisted automations offload repetitive, error‑prone tasks to a predictable workflow. Instead of manual copy‑paste and ad‑hoc scripts, your team gets a governed pipeline with versioned state, auditability, and observable runs.

n8n’s node graph makes data flow transparent while AI‑powered enrichment (classification, extraction, summarization) boosts throughput and consistency. Teams reclaim time, reduce operational costs, and standardize best practices without sacrificing flexibility.

Compared to one‑off integrations, an AI agent is easier to extend: swap APIs, add filters, or bolt on notifications without rewriting everything. You get reliability, control, and a faster path from idea to production.

Best Practices

• Credentials: restrict scopes and rotate tokens regularly.
• Resilience: configure retries, timeouts, and backoff for API nodes.
• Data Quality: validate inputs; normalize fields early to reduce downstream branching.
• Performance: batch records and paginate for large datasets.
• Observability: add failure alerts (Email/Slack) and persistent logs for auditing.
• Security: avoid sensitive data in logs; use environment variables and n8n credentials.

FAQs

Can I swap integrations later? Yes. Replace or add nodes and re‑map fields without rebuilding the whole flow.

How do I monitor failures? Use Execution logs and add notifications on the Error Trigger path.

Does it scale? Use queues, batching, and sub‑workflows to split responsibilities and control load.

Is my data safe? Keep secrets in Credentials, restrict token scopes, and review access logs.