Multi-Modal Expense Tracking with Telegram, Gemini AI & Google Sheets

Go to Workflow
0 views
Built by OwenLee OwenLee
Created on June 13, 2026

Description

🀯 Problem of Traditional Bookkeeping
πŸ”€ Context switch kills the habit: Because bookkeeping lives outside the apps you use every day, you postpone it β†’ forget to log.
🧱 High input friction: You’re forced to fill rigid fields (amount/category/date/notes…), which is slow and discouraging for quick capture.
πŸŽ™οΈπŸ’Έ Weak or pricey natural-language options: A few tools support voice/chat, but they’re often expensive, and the experience is hit-or-miss.
πŸ”’πŸ“¦ Limited data ownership: Records live on third-party servers, so privacy and control are diluted.

πŸ“² How This Workflow Fixes It
πŸ’¬ Put the capture back where you already are: Log expenses directly inside Telegram (or other channels) in a familiar chatβ€”no new app to learn.
⚑ Ultra-low-friction, unstructured input: Send text, a voice note, or a receipt photoβ€”the flow extracts amount Β· item Β· date, supports multiple languages and relative dates, and can split multiple expenses from one message.
πŸ—‚οΈπŸ“ Your data, your sheet: Final records are written to your own Google Sheet (columnar fields or a JSON column). You keep full control.

πŸ”— Demo Google Sheet:Β click me

πŸ‘₯ Who Is This For
😀 Anyone fed up with traditional bookkeeping but curious about an AI-assisted, chat-based way to log expenses.
πŸ€– People who tried AI bookkeeping apps but found them pricey, inflexible, or clunky.
πŸ’΅ Bookkeeping beginners who want frictionless capture first, simple review and categorize later.

🧩 How It Works
πŸ’¬ Captures expenses from Telegram (text, voice note, or receipt photo).
πŸ”Ž Normalizes inputs into raw text (uses Gemini to transcribe voice and extract text from images).
🧠 Parses amount · item · date with an LLM expense parser.
πŸ“Š Appends tidy rows to Google Sheets.
πŸ”” Sends a Telegram confirmation summarizing exactly what was recorded.

πŸ› οΈ How to Set Up

1) πŸ”‘ Connect credentials (once)
TELEGRAM_BOT_TOKEN
LLM_API_KEY
GOOGLE_SHEETS_OAUTH

2) πŸš€ Quick Start
Setup:* Create a Google Sheet to store *Log Expense** data and configure it in n8n.
Telegram:* Fill in and verify the *Telegram chatId**.
Remember enable the workflow!*

🧰 How to Customize the Workflow
πŸ“ Other user interaction channels: Add Gmail, Slack, or a website Webhook to accept email/command/form submissions that map into the same parser.
🌍 Currency: Extract and store currency in its own column (e.g., MYR, USD); keep amount numeric only (no symbols).
πŸ”Ž Higher-accuracy OCR / STT to reduce errors

πŸ“© Help
Contact: [email protected]

Nodes Used (7)

AI Agent
@n8n/n8n-nodes-langchain.agent
Auto-fixing Output Parser
@n8n/n8n-nodes-langchain.outputParserAutofixing
Google Gemini
@n8n/n8n-nodes-langchain.googleGemini
Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini
Google Sheets
n8n-nodes-base.googleSheets
Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured
Telegram
n8n-nodes-base.telegram