Run a multimodal WhatsApp AI assistant with OpenAI for text, voice and images

by Dr. Firas ✓ · 503 views · created 2026-07-18 · Support Chatbot, AI Chatbot

What this workflow does

This AI workflow has 30 nodes and runs on WhatsApp events (messages). Along the way it connects WhatsApp Business Cloud, OpenAI and OpenAI Chat Model.

How it runs

Trigger: On WhatsApp events (messages).

1. Configuration (Edit Fields (Set)): sets 9 fields: whatsapp_phone_number_id, image_command, image_size…
2. Input type (Switch): routes items into 4 branches
3. Is image request? (If): checks a condition and branches into true / false
4. Get Audio Url (WhatsApp Business Cloud): media url get
5. Get Image Url (WhatsApp Business Cloud): media url get
6. Only PDF File (If): checks a condition and branches into true / false
7. Not supported (WhatsApp Business Cloud): send
8. Generate image (OpenAI): work with image
9. Text (Edit Fields (Set)): sets 1 field: text
10. Download Audio (HTTP Request): calls an HTTP API

…plus 17 more steps. See the full node list below.

Services it uses

WhatsApp Business CloudOpenAIOpenAI Chat Model

Before you upgrade to n8n 3.0

Nodes used (12)

• WhatsApp Triggern8n-nodes-base.whatsAppTrigger
• Edit Fields (Set)n8n-nodes-base.set
• Switchn8n-nodes-base.switch
• Ifn8n-nodes-base.if
• OpenAI@n8n/n8n-nodes-langchain.openAi
• WhatsApp Business Cloudn8n-nodes-base.whatsApp
• AI Agent@n8n/n8n-nodes-langchain.agent
• OpenAI Chat Model@n8n/n8n-nodes-langchain.lmChatOpenAi
• Simple Memory@n8n/n8n-nodes-langchain.memoryBufferWindow
• HTTP Requestn8n-nodes-base.httpRequest
• Extract from Filen8n-nodes-base.extractFromFile
• Coden8n-nodes-base.code

From the author

Quick overview This workflow turns WhatsApp into a multimodal assistant that answers text, voice notes, images, and PDF documents using OpenAI, and can generate images with DALL·E on demand, replying back in WhatsApp with either text, audio, or an image. How…

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