Templates / Build a multi-modal Telegram AI assistant with Gemini, voice & image generation

Build a multi-modal Telegram AI assistant with Gemini, voice & image generation

Needs changes

by Iniyavan JC ✓ · 3,962 views · created 2025-07-14 · Personal Productivity, AI Chatbot

Needs changes. This template uses 1 thing(s) that n8n 3.0 removes: Read Binary File. 1 breaking item(s) found. Static check, last run 2026-10-19.

What this workflow does

This AI workflow has 84 nodes and runs on Telegram events (message). Along the way it connects MongoDB, Google Gemini Chat Model, MongoDB Chat Memory and Telegram and 4 more. It also calls api.assemblyai.com and api.together.xyz over HTTP.

How it runs

Trigger: On Telegram events (message).

  1. Toggle GF Mode (Switch): routes items into 2 branches
  2. Set GF Mode TRUE (Edit Fields (Set)): sets or maps fields
  3. Set GF Mode FALSE (Edit Fields (Set)): sets or maps fields
  4. Check Voice Message (If): checks a condition and branches into true / false
  5. Google Sheets: append or update
  6. Google Sheets: append or update
  7. HTTP Request: calls an HTTP API
  8. Extract & Validate Data (Code): runs custom JavaScript code
  9. Send Mode Confirmation : /gf_on (Telegram): uses Telegram
  10. Send Mode Confirmation : /gf_off (Telegram): uses Telegram

…plus 65 more steps. See the full node list below.

Services it uses

MongoDBGoogle Gemini Chat ModelMongoDB Chat MemoryTelegramGoogle TasksGoogle CalendarGoogle Cloud Natural LanguageGoogle Sheets

HTTP calls to: api.assemblyai.com, api.together.xyz

Before you upgrade to n8n 3.0

1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:

  • Read Binary File in Read MP3 File1: replace with Read/Write Files from Disk.

Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).

Removed in 3.0Replace with
Read Binary File
Read MP3 File1
Read/Write Files from Disk

Nodes used (21)

From the author

How it works This workflow creates a multi-talented AI assistant named Simran that interacts with users via Telegram. It can handle text and voice messages, understand the user's intent, and perform various tasks. Step 1: Receive & Transcribe Input The…

Excerpt from Iniyavan JC's description on n8n.io.

View the original on n8n.io → Check your own copy

Get the weekly “what broke” email

New templates, newly broken ones, and n8n release changes. One short email a week.

Form not loading? Subscribe here.