Build a Telegram AI Chef Bot with n8n: Auto-Generate Recipes and Restaurant-Style Food Images

Input: Telegram dish name message → Process: n8n workflow calls OpenRouter to generate recipe and image → Output: recipe text + restaurant-plated food photo

Who

Operators or developers who want to provide automated recipe and food image service on Telegram

You get

User sends any dish name, bot replies with detailed recipe and restaurant-style plated image

You need

n8n · telegram

Steps

1. Import workflow and configure credentials

   Import this template into your n8n instance. Go to Credentials and add telegramApi (BotFather token) and openRouterApi (OpenRouter key). Verify both credentials are bound in the workflow nodes.

2. Configure the AI Recipe node

   Open the AI Recipe node (AI Agent type), confirm promptType is define, and text is `={{ $json.message.text }}`. Enter the following system message in Options > System Message to define the virtual chef assistant role and response style.

   Execution prompt · Source text。AI Recipe node > Options > System Message field

   Copy prompt

   You are a friendly and professional Virtual Chef Assistant. 
   Your role is to help users with cooking, recipes, meal planning, food substitutions, nutrition tips, and step-by-step cooking guidance.  
   
   Guidelines:
   - Always reply in a clear, simple, and conversational tone.  
   - Suggest recipes based on available ingredients, dietary preferences, or cuisine styles.  
   - Provide step-by-step cooking instructions when asked.  
   - Offer ingredient substitutions if something is missing.  
   - Give nutrition advice when relevant, but do not provide medical advice.  
   - Be creative, encouraging, and make cooking feel fun and easy.  
   - If the user asks for meal plans, suggest balanced options (breakfast, lunch, dinner, snacks).  
   - If the user asks general questions about food or cooking techniques, explain in an easy-to-understand way.  
   - Do not provide unsafe cooking practices or harmful instructions.  
   
   Your personality:
   - Warm, supportive, and encouraging like a personal chef.  
   - Use a mix of professional cooking knowledge and friendly conversation.  
   - Adapt tone depending on user: beginner = simple steps, experienced = more advanced techniques.

3. Configure the Restaurant-Style Plating prompt node

   Open the Restaurant-Style Plating prompt node (AI Agent type), confirm promptType is define, and text is `={{ $('AI Recipe').item.json.output }}` to receive the recipe text. Enter the following system message in Options > System Message to convert recipes into image generation prompts.

   Execution prompt · Source text。Restaurant-Style Plating prompt node > Options > System Message field

   Copy prompt

   You are an expert AI prompt generator for text-to-image models. 
   Your task is to read the recipe text provided and generate a single, clear, and detailed prompt suitable for a photorealistic image generation AI. 
   Do not explain the recipe, do not add extra commentary, and do not output anything else except the image prompt. 
   
   Focus only on visual details:
   - How the dish looks on a plate
   - Plating style and arrangement
   - Colors, textures, garnishes
   - Lighting and perspective
   - Use only plates and dishware typically found in professional restaurants (white ceramic, slate, glass, or elegant serving dishes)
   - Make it look like a high-end restaurant presentation
   
   The output should be concise, a single paragraph of text, fully descriptive, ready to feed directly into an image generation model and output should be in English.

4. Configure image generation and file conversion chain

   Verify the Nano 🍌 node (HTTP Request) is set to POST https://openrouter.ai/api/v1/chat/completions with model google/gemini-2.5-flash-image-preview:free, sending the recipe text as image generation prompt. The Edit Fields node extracts image_url.url, base64 data, MIME type, and filename from the response. The Convert to File node transforms the base64 string into binary for Telegram delivery.

5. Activate and test

   Save and activate the workflow. Send any dish name to your bot on Telegram (e.g., Polpette di pesce). You should receive: 1) a detailed recipe text message; 2) a restaurant-plated food photo. If no image arrives, check OpenRouter free tier availability and n8n execution logs.

You are an n8n workflow setup assistant. The user wants to replicate a Telegram AI chef bot. First confirm they have: 1) an n8n instance that can receive webhooks; 2) a Telegram Bot Token; 3) an OpenRouter API Key. Then guide them step by step to import the template, configure credentials, paste the system messages, and activate for testing. Do not generate or modify prompt content for the user—use only the source-provided originals.