Skip to main content

Process receipts with Google Vision OCR, AI & Telegram to Google Sheets

Workflow preview

Workflow preview
100%
Process receipts with Google Vision OCR, AI & Telegram to Google Sheets preview
Open on n8n.io

Important notice

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

1. Workflow Overview

Automated Financial Reporting Using Google Vision OCR, Telegram & Google Sheets This workflow automates the process of recording financial transactions from photos of receipts or shopping receipts....

Best for

  • Invoice Processing automation workflows
  • AI Summarization automation workflows
  • advanced n8n builders looking for reusable templates

Tools used

n8n-nodes-base.telegramtrigger, n8n-nodes-base.if, n8n-nodes-base.httprequest, n8n-nodes-base.set, n8n-nodes-base.code, @n8n/n8n-nodes-langchain.chainllm, @n8n/n8n-nodes-langchain.lmchatopenrouter, @n8n/n8n-nodes-langchain.outputparserstructured

Source and attribution

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

Original n8n.io source

1.1 Workflow description

Title
Process receipts with Google Vision OCR, AI & Telegram to Google Sheets
Workflow name
Process receipts with Google Vision OCR, AI & Telegram to Google Sheets

Automated Financial Reporting Using Google Vision OCR, Telegram & Google Sheets

This workflow automates the process of recording financial transactions from photos of receipts or shopping receipts. Users simply send an image of the receipt via Telegram. The image is processed using the Google Vision API to detect text, then extracted and structured by LLM via OpenRouter. The final result is saved to Google Sheets and also displayed to the user via a Telegram bot.

đź§ľ Google Sheets Template Create a Google Sheet using this template: Financial Reporting

🛠️ Key Features

  • The workflow starts when a user sends a photo of a receipt to the Telegram bot.
  • The image is converted to text using the Google Vision API's OCR.
  • Data processing with LLM (OpenRouter) helps identify and structure transaction elements such as: date, vendor name & address, receipt/invoice number, item list (product name, quantity, unit price, total), and transaction category.
  • Cleaned and structured data is automatically recorded to Google Sheets per item.
  • The system also sends a summary of the recording results in an easy to read text format.
  • Users can also send text messages to the bot to query stored transaction data, which will be answered by a Google Sheets-based AI Agent.

đź”§ Requirements

  • Active Telegram Bot + API Token
  • Google Vision API Key
  • OpenRouter Account + API Key
  • Google Sheets connected to n8n

đź§© Setup Instructions

  1. Replace all API keys and tokens with your own in the relevant nodes.
    • Google Vision API Key: Set in 'Set Vision API' node.
    • Telegram Bot Token: Set in 'Set Telegram Token' node and all Telegram nodes.
    • OpenRouter API Key: Set in all OpenRouter nodes.
    • Google Sheets: Connect your own Google Sheets credential.
  2. Use the provided Google Sheets template or your own.
  3. Activate the workflow after configuration.
  4. (Optional) Review sticky notes for step-by-step explanations.

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 - Telegram Trigger

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

Block 2 - If

Type / Role
n8n-nodes-base.if - if
Config choices
Version 2.2

Block 3 - Get Path

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

Block 4 - Get URL

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

Block 5 - Set Vision API

Type / Role
n8n-nodes-base.set - set
Config choices
Version 3.4

Block 6 - HTTP Request

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

Block 7 - Code

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

Block 8 - Basic LLM Chain

Type / Role
@n8n/n8n-nodes-langchain.chainLlm - chainLlm
Config choices
Version 1.7

Block 9 - OpenRouter Chat Model

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

Block 10 - Structured Output Parser

Type / Role
@n8n/n8n-nodes-langchain.outputParserStructured - outputParserStructured
Config choices
Version 1.3

Block 11 - Append or update row in sheet

Type / Role
n8n-nodes-base.googleSheets - googleSheets
Config choices
Version 4.6

Block 12 - Split Out

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

Block 13 - Basic LLM Chain1

Type / Role
@n8n/n8n-nodes-langchain.chainLlm - chainLlm
Config choices
Version 1.7

Block 14 - OpenRouter Chat Model1

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

Block 15 - Send a text message

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

Block 16 - AI Agent

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

Block 17 - Get row(s) in sheet in Google Sheets

Type / Role
n8n-nodes-base.googleSheetsTool - googleSheetsTool
Config choices
Version 4.6

Block 18 - OpenRouter Chat Model2

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

Block 19 - Send a text message1

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

Block 20 - Simple Memory

Type / Role
@n8n/n8n-nodes-langchain.memoryBufferWindow - memoryBufferWindow
Config choices
Version 1.3

Block 21 - Code1

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

Block 22 - Send a text message2

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

Block 23 - Set Telegram Token

Type / Role
n8n-nodes-base.set - set
Config choices
Version 3.4

Block 24 - Sticky Note

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

Showing the first 24 of 31 workflow blocks. Download the JSON for the full node graph.

3. Summary Table

Workflow Process receipts with Google Vision OCR, AI & Telegram to Google Sheets
Complexity advanced
Nodes 31
Categories Invoice Processing, AI Summarization
Author Budi SJ
Published 24 Jul 2025

4. Reproducing the Workflow from Scratch

  1. 1. Download the workflow JSON

    Use the JSON export at /data/workflows/6359/6359.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 Process receipts with Google Vision OCR, AI & Telegram to Google Sheets do?

Automated Financial Reporting Using Google Vision OCR, Telegram & Google Sheets This workflow automates the process of recording financial transactions from photos of receipts or shopping receipts....

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 Invoice Processing, AI Summarization use case.