Multi-Modal Telegram AI Assistant with Gemini, Voice & Image Gen - n8n Workflow | Neura Market
Multi-Modal Telegram AI Assistant with Gemini, Voice & Image Gen
Builds a Telegram bot that handles text/voice inputs, understands intent via LLM, generates images/voice, sets reminders, and maintains memory with MongoDB.
This n8n workflow creates an advanced multi-modal AI assistant named Simran for Telegram, capable of processing text and voice messages. It transcribes voice via AssemblyAI, analyzes intent with a Large Language Model (likely Gemini), fetches conversation context from MongoDB, and routes to specialized tasks: general chat with customizable personality (standard or 'Girlfriend Mode') and mood analysis, image generation from prompts, reminder setting via Google Calendar and Tasks, or saving user i
Platform
n8n
Category
IT & Development
Price
$24.99
Creator
Jordi Faber
Telegram
AI Assistant
Gemini
Voice Transcription
Image Generation
MongoDB
Google Calendar
Reminders
Agentic AI
AssemblyAI
How to import this workflow into n8n
1Purchase or download the workflow to get the n8n workflow JSON file.
2In your n8n instance, open Workflows and choose "Import from File" (or paste the JSON with Ctrl+V on the canvas).
3Open each node marked with a credential warning and connect your own accounts and API keys.
4Run the workflow once manually to verify the data flow, then toggle it to Active.