Multi-modal expense tracking with GPT-4, Gemini OCR, and voice via Telegram
Needs changesWhat this workflow does
This AI workflow has 24 nodes and runs when an MCP client calls one of its tools (plus 1 other trigger). Along the way it connects Telegram, MCP Client, Google Sheets and HTTP Request and 2 more. It also calls api.elevenlabs.io over HTTP.
How it runs
Trigger: When an MCP client calls one of its tools (plus 1 other trigger).
- Route Input by Message Type (Switch): routes items into 3 branches
- Rename Fields (Edit Fields (Set)): sets 1 field: Prompt
- Get Voice File from Telegram (Telegram): work with file
- Download Receipt Image (Telegram): work with file
- Classify Message Intent (Basic LLM Chain): sends a prompt to an LLM, with model: Intent Classification Model
- Convert Voice to Text (ElevenLabs) (HTTP Request): calls api.elevenlabs.io (POST)
- Extract Receipt Data (Google Gemini): analyze (image)
- Route to Expense or Query Processing (If): checks a condition and branches into true / false
- Agent (AI Agent): runs an AI agent, with model: Main Financial Assistant; 1 tool (MCP Client)
- Parse and Split Multiple Expenses (Basic LLM Chain): sends a prompt to an LLM, with model: Expense Parsing Model
…plus 1 more step. See the full node list below.
Services it uses
HTTP calls to: api.elevenlabs.io
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in Agent (v1.7): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) Agent (v1.7) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (15)
- AI Agent
@n8n/n8n-nodes-langchain.agent - Telegram Trigger
n8n-nodes-base.telegramTrigger - MCP Client Tool
@n8n/n8n-nodes-langchain.mcpClientTool - MCP Server Trigger
@n8n/n8n-nodes-langchain.mcpTrigger - Calculator
@n8n/n8n-nodes-langchain.toolCalculator - Google Sheets Tool
n8n-nodes-base.googleSheetsTool - Http Request Tool
n8n-nodes-base.httpRequestTool - Edit Fields (Set)
n8n-nodes-base.set - Telegram
n8n-nodes-base.telegram - HTTP Request
n8n-nodes-base.httpRequest - Switch
n8n-nodes-base.switch - Google Gemini
@n8n/n8n-nodes-langchain.googleGemini - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - If
n8n-nodes-base.if - Azure OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatAzureOpenAi
From the author
This n8n template creates an intelligent expense tracking system 🤖 that processes text, voice, and receipt images through Telegram. The assistant automatically categorizes expenses, handles currency conversions 🌍, and maintains financial records in Google…