Skip to main content

Extract business card data from Telegram to Google Sheets with OpenRouter AI Vision

Workflow preview

Workflow preview
100%
Extract business card data from Telegram to Google Sheets with OpenRouter AI Vision preview
Open on n8n.io

Important notice

This workflow is provided as-is. Please review and test before using in production.

1. Workflow Overview

Title (suggested): Extract business card data from Telegram to Google Sheets Who’s it for Teams that receive business cards digitally (sales, marketing, back office) and want a plug and play way to...

Best for

  • Document Extraction automation workflows
  • AI Summarization automation workflows
  • intermediate n8n builders looking for reusable templates

Tools used

n8n-nodes-base.googlesheets, n8n-nodes-base.if, @n8n/n8n-nodes-langchain.agent, @n8n/n8n-nodes-langchain.lmchatopenrouter, @n8n/n8n-nodes-langchain.outputparserstructured, n8n-nodes-base.telegramtrigger, n8n-nodes-base.stickynote

Source and attribution

This workflow is cataloged by N8N Workflows and links back to its original n8n.io source page by Haruki Kuwai.

Original n8n.io source

1.1 Workflow description

Title
Extract business card data from Telegram to Google Sheets with OpenRouter AI Vision
Workflow name
Extract business card data from Telegram to Google Sheets with OpenRouter AI Vision

Title (suggested):

Extract business card data from Telegram to Google Sheets

Who’s it for

Teams that receive business cards digitally (sales, marketing, back-office) and want a plug-and-play way to capture contacts into a sheet without manual typing.

What it does / How it works

This workflow ingests a business card sent to your Telegram bot, detects whether the message contains an image or text, extracts key fields with an AI Vision Agent (company, full name, department, job title, postal code, address, phone, mobile, fax, email, website), and appends or updates a contact row in Google Sheets automatically.

How to set up

Connect Telegram (bot token) and enable file download.

Connect your AI provider (OpenRouter or equivalent) used by the AI Vision Agent.

Connect Google Sheets and select your spreadsheet + sheet tab.

Rename nodes clearly and keep sticky notes: one overview note (this description) + step notes.

Test by sending a sample card image to your bot and verify the row is appended/updated.

Requirements

Telegram Bot API credential

AI chat/vision credential

Google Sheets OAuth credential and an accessible spreadsheet

How to customize the workflow

Map fields to your sheet headers (add/remove columns as needed).

Adjust the system prompt to prefer your locale or specific field formats.

Change the matching key for update logic (e.g., company name or email).

Add downstream steps (CRM push, dedupe rules, notifications).

Security note: Do not hardcode API keys or include real IDs/emails. Use credentials and environment configs only.

JSON

[ { "company_name": "Example Company Ltd.", "department": "Sales", "job_title": "Sales Manager", "full_name": "Taro Yamada", "postal_code": "100-0001", "address": "1-1-1 Marunouchi, Chiyoda-ku, Tokyo", "phone_number": "+81-3-0000-0000", "mobile_phone_number": "+81-90-0000-0000", "fax_number": "+81-3-1111-1111", "email": "[email protected]", "website_url": "https://example.com" } ]

Troubleshooting

Nothing appears in Google Sheets

Solution: Verify that your Google Sheets credentials are correctly authorized.

Confirm the Spreadsheet ID and Sheet Name in the node match your target file.

Make sure the Google Sheets node is connected downstream of the AI Vision Agent.

If the workflow runs successfully but nothing is added, check whether the matching column (company_name) already exists — in appendOrUpdate mode it will only update that row.

AI returns incomplete or invalid data

Solution: Review the system prompt in the AI Vision Agent to ensure it instructs the model to return a structured JSON object with all required fields (company name, full name, department, job title, address, etc.).

If the result is partial, verify the image quality of the uploaded business card — low contrast or skewed images can reduce OCR accuracy.

You can reduce temperature in the AI node to make output more deterministic.

Workflow doesn’t start automatically

Solution: Check that the workflow is activated (toggle is ON in the top right of n8n).

Verify the Webhook URL is correctly registered in Telegram’s bot settings.

Run manually once to ensure all credentials and nodes are configured correctly.

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 - Add to Google Sheet

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

Block 2 - Check Input Type

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

Block 3 - AI Vision Agent

Type / Role
@n8n/n8n-nodes-langchain.agent - agent
Config choices
Version 2

Block 4 - OpenAI Vision Model

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

Block 5 - Ingredient Parser

Type / Role
@n8n/n8n-nodes-langchain.outputParserStructured - outputParserStructured
Config choices
Version 1.2

Block 6 - Telegram Trigger

Type / Role
n8n-nodes-base.telegramTrigger - telegramTrigger
Config choices
Version 1.2

Block 7 - Sticky Note

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

Block 8 - Sticky Note1

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

Block 9 - Sticky Note2

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

Block 10 - Sticky Note3

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

Block 11 - Sticky Note4

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

Block 12 - Sticky Note5

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

3. Summary Table

Workflow Extract business card data from Telegram to Google Sheets with OpenRouter AI Vision
Complexity intermediate
Nodes 12
Categories Document Extraction, AI Summarization
Author Haruki Kuwai
Published 16 Oct 2025

4. Reproducing the Workflow from Scratch

  1. 1. Download the workflow JSON

    Use the JSON export at /data/workflows/9754/9754.json as the source template for this automation.

  2. 2. Import the template into n8n

    Open n8n, import the downloaded JSON, and review each node before activating the workflow.

  3. 3. Configure credentials and variables

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

  4. 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. 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.

Frequently asked questions

What does Extract business card data from Telegram to Google Sheets with OpenRouter AI Vision do?

Title (suggested): Extract business card data from Telegram to Google Sheets Who’s it for Teams that receive business cards digitally (sales, marketing, back office) and want a plug and play way to...

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 Document Extraction, AI Summarization use case.