Analyze customer sales calls and update CRM with Whisper and GPT-4

Open on n8n.io

$20/month : Unlimited workflows

2500 executions/month

Try free

THE #1 IN WEB SCRAPING

Scrape any website without limits

Try free

HOSTINGER

Early Deal
DISCOUNT 20%

Self-hosted n8n

Unlimited workflows - from $4.99/mo

Try free

#1 hub for scraping, AI & automation

6000+ actors - $5 credits/mo

Try free

1. Workflow Overview

AI Customer Call Analyzer — Voice → Insights → CRM with GPT 4 Converts raw sales call recordings into structured CRM intelligence. Uploads audio → transcribes via Whisper → GPT 4 extracts intent, s...

Best for

CRM automation workflows
AI Summarization automation workflows
advanced n8n builders looking for reusable templates

Tools used

n8n-nodes-base.stickynote, n8n-nodes-base.webhook, n8n-nodes-base.code, n8n-nodes-base.httprequest, n8n-nodes-base.wait, @n8n/n8n-nodes-langchain.agent, @n8n/n8n-nodes-langchain.lmchatopenai, n8n-nodes-base.emailsend

Source and attribution

This workflow is cataloged by N8N Workflows and links back to its original n8n.io source page by Oneclick AI Squad.

Original n8n.io source

1.1 Workflow description

Title: Analyze customer sales calls and update CRM with Whisper and GPT-4
Workflow name: Analyze customer sales calls and update CRM with Whisper and GPT-4

AI Customer Call Analyzer — Voice → Insights → CRM with GPT-4

Converts raw sales call recordings into structured CRM intelligence. Uploads audio → transcribes via Whisper → GPT-4 extracts intent, sentiment, objections, next steps → updates CRM and sends a structured summary to the sales team.

How it works

Upload Call Recording - Webhook receives audio file upload (mp3, wav, m4a) from sales rep portal
Validate & Prepare Audio - Checks file type, size limits, extracts call metadata
Transcribe via Whisper - Sends audio to OpenAI Whisper API for high-accuracy transcription
Wait — Transcription Buffer - Holds until transcription is confirmed complete
GPT-4 Call Intelligence - Extracts intent, sentiment, objections, buying signals, action items
MCP Context Enrichment - Pulls CRM history and enriches analysis with account context
Update CRM Record - Writes structured insights back to CRM (HubSpot / Salesforce)
Send Sales Summary - Emails rep and manager with call scorecard and next steps
Audit Log - Records all processing steps for compliance and coaching

Setup Steps

Import this workflow into n8n
Configure credentials:

OpenAI API - For Whisper transcription and GPT-4 analysis
HubSpot / Salesforce - CRM update target
Google Sheets - Audit log and call registry
SMTP / Gmail - Sales summary delivery

Set your CRM API endpoint and field mapping in the update node
Configure your sales team email list in the notify node
Activate the workflow

Sample Upload Payload

{
 "callId": "CALL-20250222-0042",
 "repEmail": "[email protected]",
 "repName": "Jane Smith",
 "contactEmail": "[email protected]",
 "contactName": "Bob Johnson",
 "companyName": "Acme Corp",
 "dealStage": "negotiation",
 "callDurationSecs": 1847,
 "audioUrl": "https://storage.company.com/calls/call-0042.mp3"
}

Features

Whisper-powered transcription with speaker diarization hints
GPT-4 intent and sentiment extraction with confidence scores
Objection and buying signal detection
Auto CRM field mapping — no manual data entry
Sales scorecard with talk ratio, next step clarity, deal risk
Full audit trail for call coaching and compliance

Explore More LinkedIn & Social Automation: Contact us to design AI-powered lead nurturing, content engagement, and multi-platform reply workflows tailored to your growth strategy.

1.2 Logical Blocks

This catalog entry is organized from the workflow JSON. The node-level section below shows the executable blocks available for review before importing the template.

2. Block-by-Block Analysis

Block 1 - Sticky Note

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 2 - Sticky Note1

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 3 - Sticky Note2

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 4 - Sticky Note3

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 5 - Sticky Note4

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 6 - Receive Call Recording Upload

Type / Role: n8n-nodes-base.webhook - webhook
Config choices: Version 2

Block 7 - Validate Call Metadata and Audio

Type / Role: n8n-nodes-base.code - code
Config choices: Version 2

Block 8 - Fetch Audio File from URL

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

Block 9 - Transcribe Audio with OpenAI Whisper

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

Block 10 - Wait — Transcription Buffer (15 sec)

Type / Role: n8n-nodes-base.wait - wait
Config choices: Version 1.1

Block 11 - Parse and Structure Transcript

Type / Role: n8n-nodes-base.code - code
Config choices: Version 2

Block 12 - Fetch CRM Contact History

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

Block 13 - GPT-4 Call Intelligence Analysis

Type / Role: @n8n/n8n-nodes-langchain.agent - agent
Config choices: Version 1.6

Block 14 - GPT-4 Model

Type / Role: @n8n/n8n-nodes-langchain.lmChatOpenAi - lmChatOpenAi
Config choices: Version 1

Block 15 - Parse GPT-4 Intelligence Output

Type / Role: n8n-nodes-base.code - code
Config choices: Version 2

Block 16 - Update CRM Contact and Deal

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

Block 17 - Log Call Activity in CRM

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

Block 18 - Send Call Intelligence Summary to Sales Team

Type / Role: n8n-nodes-base.emailSend - emailSend
Config choices: Version 2.1

Block 19 - Write to Call Analytics Audit Log

Type / Role: n8n-nodes-base.googleSheets - googleSheets
Config choices: Version 4.5

Block 20 - Build Final Processing Response

Type / Role: n8n-nodes-base.code - code
Config choices: Version 2

Block 21 - Return Processing Confirmation

Type / Role: n8n-nodes-base.respondToWebhook - respondToWebhook
Config choices: Version 1

3. Summary Table

Workflow	Analyze customer sales calls and update CRM with Whisper and GPT-4
Complexity	advanced
Nodes	21
Categories	CRM, AI Summarization
Author	Oneclick AI Squad
Published	22 Feb 2026

4. Reproducing the Workflow from Scratch

1. Download the workflow JSON

Use the JSON export at /data/workflows/13593/13593.json as the source template for this automation.
2. Import the template into n8n

Open n8n, import the downloaded JSON, and review each node before activating the workflow.
3. Configure credentials and variables

Replace placeholder credentials, API keys, webhook URLs, account IDs, and environment-specific values with your own settings.
4. Test with sample data

Run the workflow manually or in a staging workspace, inspect node output, and confirm downstream systems receive the expected data.
5. Activate and monitor

Enable the workflow only after testing, then monitor executions, errors, and rate limits during the first production runs.

5. General Notes & Resources

Review imported nodes carefully before activation. This catalog entry is intended to help you inspect the workflow structure, understand required services, and find related templates faster.

Node names, credentials, schedules, webhook paths, and external service limits may need adjustment for your workspace.

Download workflow JSON Original n8n.io source CRM workflows AI Summarization workflows

Frequently asked questions

What does Analyze customer sales calls and update CRM with Whisper and GPT-4 do?

What do I need before importing this workflow?

Review the workflow JSON, configure any required credentials in n8n, and test the automation in a safe workspace before using it in production.

Can I customize this workflow?

Yes. Use the block-by-block analysis and the downloadable JSON to inspect each node, then adjust credentials, prompts, schedules, filters, or destinations for your CRM, AI Summarization use case.

Oneclick AI Squad

224 workflows

Nodes

n8n-nodes-base.stickynote n8n-nodes-base.webhook n8n-nodes-base.code n8n-nodes-base.httprequest n8n-nodes-base.wait @n8n/n8n-nodes-langchain.agent @n8n/n8n-nodes-langchain.lmchatopenai n8n-nodes-base.emailsend

Complexity

advanced

Published 22 Feb 2026

Likes 0

View on n8n.io Download Workflow

Install path: /data/workflows/13593/13593.json

Share Your Workflow

Have a useful automation to share? Publish it and help the community.

Submit Your Template How to Submit

Related Workflows

Send low-stock inventory reorder emails from Snowflake with Claude and Outlook

## Quick overview This workflow runs daily, queries Snowflake for items at or below their reorder level, and groups them by supplier. For each supplier, it uses Anthropic Claude to draft a reorder email, optionally appends details to a Google Docs log, and sends the email via Microsoft Outlook. ## How it works 1. A Schedule Trigger fires every day at 07:00 (Europe/Helsinki timezone) and passes through a Workflow Config node that holds your optional Google Docs log ID. 2. A Snowflake query fetches all inventory rows where current_stock <= reorder_level. If no items qualify, the workflow exits cleanly via a Pass Through node with no further action. 3. A Code node groups the low-stock items by supplier_name, producing one batch per vendor. A SplitInBatches loop then processes each supplier one at a time. 4. For each supplier, a Set node extracts the supplier email, item count, and a pre-rendered Markdown item list, then passes everything to an LLM chain powered by Claude (claude-sonnet-4-6). 5. Claude generates a concise, professional reorder request email body in Markdown, constrained by a system prompt to return only the email content with no preamble. 6. The Markdown output is converted to HTML and optionally appended as a one-line entry to a Google Docs audit log (skipped if no doc ID is configured). The workflow then sends the HTML email to the supplier via Microsoft Outlook before advancing to the next vendor. ## Setup 1. Open the Workflow Config node and set log_doc_id to the document ID from your Google Doc URL (the string between /d/ and /edit). Leave it empty to skip audit logging entirely. 2. Add your Snowflake credentials to the Query Snowflake DB node and verify the query matches your database name, schema, and table. The expected columns are item_id, item_name, current_stock, reorder_level, supplier_name, and supplier_email. 3. Add your Anthropic credentials to the Claude Email Generation node. 4. Add your Microsoft Outlook credentials to both the Send Reorder Email and Send Error Alert nodes. Update the toRecipients field in Send Error Alert to your alert address. 5. If logging is enabled, add your Google Docs credentials to the Log to Google Docs node. 6. In n8n Settings > Error Workflow, point to a dedicated error-handler sub-workflow that wires into the Send Error Alert node (it is intentionally unwired in this workflow). ## Requirements - Snowflake account with an inventory table containing current_stock, reorder_level, supplier_name, and supplier_email columns - Anthropic API credentials (claude-sonnet-4-6) - Microsoft 365 account with Outlook access - Google Docs OAuth2 credentials (only if audit logging is enabled) ## Customization - Adjust the Snowflake query to match your schema, add filters by warehouse or category, or join additional tables for richer item metadata. - Modify the Claude system prompt in Build Email Draft to change tone, language, or email structure — for example to generate Finnish-language emails or include purchase order references. - Change the cron expression in When 7am Daily to run at a different time or frequency. - Extend the log entry format in Log to Google Docs to include item names, SKUs, or a hyperlink back to the workflow execution. - Replace the Google Docs logging step with a Slack notification, a row insert into PostgreSQL, or any other audit destination by swapping the node after Check Configured Doc ID.

View

Flag delayed Shopify orders with Slack, Google Sheets and Gmail

## Quick overview This workflow runs daily to check Shopify for open, unfulfilled orders older than two days, classifies them by delay severity, posts a digest to Slack, logs each delayed order to Google Sheets, and emails an HTML summary report via Gmail. ## How it works 1. Runs every day at 08:00 (server time) on a schedule trigger. 2. Calls the Shopify Admin REST API to fetch up to 250 open orders with `fulfillment_status=unfulfilled`. 3. Calculates each order’s age in days and extracts key details (customer, totals, items, and Shopify Admin order link). 4. Filters to only orders delayed by 2+ days and labels each one as WARNING (2–4 days), CRITICAL (5–7 days), or ESCALATION (8+ days). 5. Checks whether any delayed orders exist and stops without notifying if the delayed list is empty. 6. Builds a Slack message grouped by severity and posts the delay digest to the configured Slack channel. 7. Appends each delayed order as a row in a Google Sheets tracker, then aggregates the list and sends an HTML summary email via Gmail to the operations manager. ## Setup 1. Add Shopify Admin API credentials (HTTP header auth) and replace `YOUR_STORE` in the Shopify API and admin order URLs with your store domain. 2. Add Slack credentials and set the target channel ID in the Slack message step. 3. Add Google Sheets credentials, set `YOUR_GOOGLE_SHEET_ID`, and ensure the worksheet named “Fulfillment Delay Tracker” exists with matching columns. 4. Add Gmail credentials and set `YOUR_OPS_MANAGER_EMAIL` to the recipient address for the summary report. 5. Adjust the cron schedule and the delay thresholds (2/5/8 days) in the filtering and severity rules if needed.

View

Assess Salesforce deal risk with Gmail, Outlook, OpenAI and Slack alerts

## Quick Overview This workflow runs every six hours to pull open Salesforce opportunities, enriches selected deals with Gmail and Microsoft Outlook email context, uses OpenAI to score deal risk, writes the assessment back to Salesforce, and notifies teams in Slack with optional email escalation for critical deals. ## How it works 1. Runs every 6 hours and queries Salesforce for up to 100 open Opportunities via the REST API. 2. Stops the run and posts a Slack message if the Salesforce fetch returns an error. 3. Normalizes each Opportunity, computes activity/close-date metrics, and routes deals with missing required fields to a Slack channel for manual data cleanup. 4. Applies a heuristic triage and immediately marks non-risky deals as healthy in Salesforce to avoid unnecessary AI analysis. 5. For triaged deals, pulls recent related messages from Gmail and Microsoft Outlook, merges them, and builds a compact email engagement context (participants, reply counts, and silence gap). 6. Sends the CRM and email context to OpenAI to produce a structured risk score, drivers, and recommended actions, then validates and cleans the AI output. 7. Updates Salesforce with the assessed risk fields and, for non-low risk deals, posts a detailed Slack alert (with cooldown suppression) and emails leadership when the risk level is Critical. ## Setup 1. Add Salesforce OAuth2 credentials, set the SALESFORCE_INSTANCE_URL environment variable, and ensure the Opportunity custom fields used for risk tracking (for example Risk_Score__c, Risk_Level__c, Risk_Summary__c, and Deal_Health__c) exist. 2. Add OpenAI credentials and confirm the selected model (gpt-4o-mini) is available in your OpenAI account. 3. Add Slack OAuth2 credentials and update the target channel IDs for Salesforce failure alerts, incomplete-deal alerts, and risk alerts. 4. Add Gmail OAuth2 credentials and Microsoft Outlook credentials (optional) so the workflow can retrieve deal-related email threads. 5. Set the LEADERSHIP_EMAIL environment variable (or edit the node default) to define where Critical-risk escalation emails are sent.

View

Need Custom Automation?

Get help designing a custom n8n workflow that connects your stack and fits your process.

Analyze customer sales calls and update CRM with Whisper and GPT-4

Workflow preview

1. Workflow Overview

Best for

Tools used

Source and attribution

1.1 Workflow description

AI Customer Call Analyzer — Voice → Insights → CRM with GPT-4

How it works

Setup Steps

Sample Upload Payload

Features

1.2 Logical Blocks

2. Block-by-Block Analysis

Block 1 - Sticky Note

Block 2 - Sticky Note1

Block 3 - Sticky Note2

Block 4 - Sticky Note3

Block 5 - Sticky Note4

Block 6 - Receive Call Recording Upload

Block 7 - Validate Call Metadata and Audio

Block 8 - Fetch Audio File from URL

Block 9 - Transcribe Audio with OpenAI Whisper

Block 10 - Wait — Transcription Buffer (15 sec)

Block 11 - Parse and Structure Transcript

Block 12 - Fetch CRM Contact History

Block 13 - GPT-4 Call Intelligence Analysis

Block 14 - GPT-4 Model

Block 15 - Parse GPT-4 Intelligence Output

Block 16 - Update CRM Contact and Deal

Block 17 - Log Call Activity in CRM

Block 18 - Send Call Intelligence Summary to Sales Team

Block 19 - Write to Call Analytics Audit Log

Block 20 - Build Final Processing Response

Block 21 - Return Processing Confirmation

3. Summary Table

4. Reproducing the Workflow from Scratch

1. Download the workflow JSON

2. Import the template into n8n

3. Configure credentials and variables

4. Test with sample data

5. Activate and monitor

5. General Notes & Resources

Frequently asked questions