AI WhatsApp Chatbot: Text, Voice, Images, PDFs + Memory
Multimodal AI assistant for WhatsApp that processes text, voice, images, and PDFs using OpenAI models, with contextual memory for natural conversations.
This advanced n8n workflow powers a WhatsApp chatbot capable of handling diverse message types: text, voice notes, images, and PDFs. It automatically detects input types and routes them to specialized OpenAI models—GPT-4o-mini for text, vision models for images, Whisper for voice transcription, and text extraction for PDFs—ensuring accurate analysis and relevant responses. Conversation memory maintains context over 10 interactions per user via session IDs, enabling coherent, personalized dialogu
Platform
n8n
Category
Education
Price
$24.99
Creator
Jose Maurino
whatsapp
chatbot
ai
openai
multimodal
gpt
whisper
tts
pdf
memory
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.