Dr. Firas This workflow corresponds to n8n.io template #17216 — we link there as the canonical source.
This workflow follows the Agent → HTTP Request recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"id": "xPNvpWRcBIuAlFNE",
"meta": {
"builderVariant": "mcp",
"aiBuilderAssisted": true
},
"name": "Run a multimodal WhatsApp AI assistant with text, voice, images, PDFs and image generation",
"tags": [],
"nodes": [
{
"id": "9c82cc24-3a8d-4847-8442-f837d0084294",
"name": "WhatsApp Trigger",
"type": "n8n-nodes-base.whatsAppTrigger",
"position": [
16,
672
],
"parameters": {
"options": {},
"updates": [
"messages"
]
},
"credentials": {
"whatsAppTriggerApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "877bf5ff-9f2e-4ba9-9843-36fe2e716ae7",
"name": "Configuration",
"type": "n8n-nodes-base.set",
"position": [
224,
672
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "cfg-phone",
"name": "whatsapp_phone_number_id",
"type": "string",
"value": ""
},
{
"id": "cfg-imgcmd",
"name": "image_command",
"type": "string",
"value": "/image"
},
{
"id": "cfg-imgsize",
"name": "image_size",
"type": "string",
"value": "1024x1024"
},
{
"id": "cfg-imgqual",
"name": "image_quality",
"type": "string",
"value": "standard"
},
{
"id": "cfg-imgstyle",
"name": "image_style",
"type": "string",
"value": "vivid"
},
{
"id": "cfg-imgcap",
"name": "image_reply_caption",
"type": "string",
"value": "\ud83d\uddbc\ufe0f Here is your image"
},
{
"id": "cfg-analyze",
"name": "image_analyze_prompt",
"type": "string",
"value": "Describe this image in detail, including any visible text."
},
{
"id": "cfg-voice",
"name": "tts_voice",
"type": "string",
"value": "onyx"
},
{
"id": "cfg-v2v",
"name": "reply_voice_to_voice",
"type": "boolean",
"value": true
}
]
},
"includeOtherFields": true
},
"typeVersion": 3.4
},
{
"id": "23c5e2b9-1bdc-415f-85cb-dbc85c57c177",
"name": "Input type",
"type": "n8n-nodes-base.switch",
"position": [
464,
624
],
"parameters": {
"rules": {
"values": [
{
"outputKey": "Text",
"conditions": {
"options": {
"version": 1,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "r-text",
"operator": {
"type": "string",
"operation": "exists",
"singleValue": true
},
"leftValue": "={{ $('WhatsApp Trigger').item.json.messages[0].text.body }}",
"rightValue": ""
}
]
},
"renameOutput": true
},
{
"outputKey": "Voice",
"conditions": {
"options": {
"version": 1,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "r-voice",
"operator": {
"type": "object",
"operation": "exists",
"singleValue": true
},
"leftValue": "={{ $('WhatsApp Trigger').item.json.messages[0].audio }}",
"rightValue": ""
}
]
},
"renameOutput": true
},
{
"outputKey": "Image",
"conditions": {
"options": {
"version": 1,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "r-image",
"operator": {
"type": "object",
"operation": "exists",
"singleValue": true
},
"leftValue": "={{ $('WhatsApp Trigger').item.json.messages[0].image }}",
"rightValue": ""
}
]
},
"renameOutput": true
},
{
"outputKey": "Document",
"conditions": {
"options": {
"version": 1,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "r-doc",
"operator": {
"type": "object",
"operation": "exists",
"singleValue": true
},
"leftValue": "={{ $('WhatsApp Trigger').item.json.messages[0].document }}",
"rightValue": ""
}
]
},
"renameOutput": true
}
]
},
"options": {
"fallbackOutput": "extra",
"renameFallbackOutput": "Not supported"
}
},
"typeVersion": 3.4
},
{
"id": "1118fb14-1013-40f5-88a1-e996e2021eed",
"name": "Is image request?",
"type": "n8n-nodes-base.if",
"position": [
1376,
-160
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": false,
"typeValidation": "loose"
},
"combinator": "and",
"conditions": [
{
"id": "c-imgreq",
"operator": {
"type": "string",
"operation": "startsWith"
},
"leftValue": "={{ $('WhatsApp Trigger').item.json.messages[0].text.body.trim().toLowerCase() }}",
"rightValue": "={{ $('Configuration').item.json.image_command.toLowerCase() }}"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "e9e29cc2-f724-40e3-b292-851fd8151ebe",
"name": "Generate image",
"type": "@n8n/n8n-nodes-langchain.openAi",
"position": [
1712,
-208
],
"parameters": {
"prompt": "={{ $('WhatsApp Trigger').item.json.messages[0].text.body.trim().substring($('Configuration').item.json.image_command.length).trim() }}",
"modelId": {
"__rl": true,
"mode": "list",
"value": "dall-e-3",
"cachedResultName": "DALL-E-3"
},
"options": {
"size": "={{ $('Configuration').item.json.image_size }}",
"style": "={{ $('Configuration').item.json.image_style }}",
"dalleQuality": "={{ $('Configuration').item.json.image_quality }}",
"returnImageUrls": false,
"binaryPropertyOutput": "data"
},
"resource": "image"
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 2.3
},
{
"id": "92eb2122-e482-40d6-b8d9-a84a9311fa07",
"name": "Send image",
"type": "n8n-nodes-base.whatsApp",
"position": [
1968,
-272
],
"parameters": {
"mediaPath": "useMedian8n",
"operation": "send",
"messageType": "image",
"phoneNumberId": "={{ $('Configuration').item.json.whatsapp_phone_number_id }}",
"additionalFields": {
"mediaCaption": "={{ $('Configuration').item.json.image_reply_caption }}"
},
"recipientPhoneNumber": "={{ $('WhatsApp Trigger').item.json.messages[0].from }}"
},
"credentials": {
"whatsAppApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "04304ede-b7f1-4f47-a442-277bce26b610",
"name": "Text",
"type": "n8n-nodes-base.set",
"position": [
1600,
-80
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "s-text",
"name": "text",
"type": "string",
"value": "={{ $('WhatsApp Trigger').item.json.messages[0].text.body }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "20ed195d-4d1a-4c40-8194-194107a5ff2d",
"name": "AI Assistant",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1824,
544
],
"parameters": {
"text": "={{ $json.text }}",
"options": {
"systemMessage": "You are a helpful, friendly multimodal WhatsApp assistant. You receive the user message as text (a plain text message, a transcribed voice note, a description of an image, or extracted PDF content). Always reply in the SAME language as the user. Keep answers concise, accurate and easy to read on a phone: short paragraphs, minimal formatting. If the user asks you to CREATE, DRAW or GENERATE an image, tell them to send a new message starting with \"/image\" followed by a short description (for example: /image a red fox in the snow) \u2014 that command runs the image generator. Never invent facts; if you are unsure, say so.",
"enableStreaming": false
},
"promptType": "define"
},
"typeVersion": 3.1
},
{
"id": "5a437bfd-1a9c-46ea-9d18-4cac195fc64c",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
1808,
704
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini",
"cachedResultName": "GPT-4O-MINI"
},
"options": {},
"builtInTools": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.3
},
{
"id": "b9528408-43c9-4775-b509-6455cca4f050",
"name": "Simple Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
1968,
704
],
"parameters": {
"sessionKey": "={{ $('WhatsApp Trigger').item.json.messages[\"0\"].from }}",
"sessionIdType": "customKey",
"contextWindowLength": 10
},
"typeVersion": 1.4
},
{
"id": "c9578f27-fe86-4040-a4fa-7201cde53914",
"name": "Get Audio Url",
"type": "n8n-nodes-base.whatsApp",
"position": [
896,
256
],
"parameters": {
"resource": "media",
"operation": "mediaUrlGet",
"mediaGetId": "={{ $('WhatsApp Trigger').item.json.messages[0].audio.id }}"
},
"credentials": {
"whatsAppApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "9a139462-b541-40cc-a71a-54290ebdd807",
"name": "Download Audio",
"type": "n8n-nodes-base.httpRequest",
"position": [
1072,
256
],
"parameters": {
"url": "={{ $json.url }}",
"options": {},
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth"
},
"typeVersion": 4.2
},
{
"id": "b923fba1-7ab9-4a04-a7ce-91a0519c824c",
"name": "Transcribe Audio",
"type": "@n8n/n8n-nodes-langchain.openAi",
"position": [
1264,
256
],
"parameters": {
"options": {},
"resource": "audio",
"operation": "transcribe"
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 2.3
},
{
"id": "ddae6e89-32ee-4c86-a76f-87a304342b53",
"name": "Audio",
"type": "n8n-nodes-base.set",
"position": [
1456,
256
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "s-audio",
"name": "text",
"type": "string",
"value": "={{ $json.text }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "e7d3a6f8-6fba-4ac5-8814-eb70d0b0b8ad",
"name": "Get Image Url",
"type": "n8n-nodes-base.whatsApp",
"position": [
928,
544
],
"parameters": {
"resource": "media",
"operation": "mediaUrlGet",
"mediaGetId": "={{ $('WhatsApp Trigger').item.json.messages[0].image.id }}"
},
"credentials": {
"whatsAppApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "7ba82382-6590-41c6-b0cb-570c00d52965",
"name": "Download Image",
"type": "n8n-nodes-base.httpRequest",
"position": [
1104,
544
],
"parameters": {
"url": "={{ $json.url }}",
"options": {},
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth"
},
"typeVersion": 4.2
},
{
"id": "1a4d0ea9-7830-4a6f-90dd-2c907207942f",
"name": "Analyze Image",
"type": "@n8n/n8n-nodes-langchain.openAi",
"position": [
1328,
544
],
"parameters": {
"text": "={{ $('Configuration').item.json.image_analyze_prompt }}",
"modelId": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini",
"cachedResultName": "GPT-4O-MINI"
},
"options": {
"detail": "auto"
},
"resource": "image",
"inputType": "base64",
"operation": "analyze"
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 2.3
},
{
"id": "44e089bf-3a5f-4550-8366-90682eb969bb",
"name": "Image",
"type": "n8n-nodes-base.set",
"position": [
1552,
544
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "s-image",
"name": "text",
"type": "string",
"value": "=User request on the image:\n{{ $('WhatsApp Trigger').item.json.messages[0].image.caption || 'Describe this image' }}\n\nImage description:\n{{ $json.content || $json.text }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "3b635465-9edf-4e49-bc29-5ae48e25524a",
"name": "Only PDF File",
"type": "n8n-nodes-base.if",
"position": [
672,
864
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "c-pdf",
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $('WhatsApp Trigger').item.json.messages[0].document.mime_type }}",
"rightValue": "application/pdf"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "faa4a720-d861-4f11-9eab-5bb3969dd90d",
"name": "Get File Url",
"type": "n8n-nodes-base.whatsApp",
"position": [
896,
816
],
"parameters": {
"resource": "media",
"operation": "mediaUrlGet",
"mediaGetId": "={{ $('WhatsApp Trigger').item.json.messages[0].document.id }}"
},
"credentials": {
"whatsAppApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "f8f29ada-d21d-475a-8084-3a08879b8fa1",
"name": "Download File",
"type": "n8n-nodes-base.httpRequest",
"position": [
1120,
816
],
"parameters": {
"url": "={{ $json.url }}",
"options": {},
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth"
},
"typeVersion": 4.2
},
{
"id": "61f2fcf0-9b2e-4f55-98ba-750ab1273769",
"name": "Extract from File",
"type": "n8n-nodes-base.extractFromFile",
"position": [
1344,
816
],
"parameters": {
"options": {},
"operation": "pdf"
},
"typeVersion": 1.1
},
{
"id": "443a07ca-f17e-46d0-ac99-a7f842bf7d86",
"name": "File",
"type": "n8n-nodes-base.set",
"position": [
1568,
816
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "s-file",
"name": "text",
"type": "string",
"value": "=User request on the file:\n{{ $('WhatsApp Trigger').item.json.messages[0].document.caption || 'Summarize this document' }}\n\nFile content:\n{{ $json.text }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "f4b075bf-4c15-45b7-85f3-2bedea6abf7e",
"name": "Incorrect format",
"type": "n8n-nodes-base.whatsApp",
"position": [
960,
976
],
"parameters": {
"textBody": "Sorry, I can only read PDF documents. Please send your file as a PDF.",
"operation": "send",
"phoneNumberId": "={{ $('Configuration').item.json.whatsapp_phone_number_id }}",
"additionalFields": {},
"recipientPhoneNumber": "={{ $('WhatsApp Trigger').item.json.messages[0].from }}"
},
"credentials": {
"whatsAppApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "b72e32eb-39ff-4c4e-a6d5-2c8a2bb6db61",
"name": "Not supported",
"type": "n8n-nodes-base.whatsApp",
"position": [
704,
1008
],
"parameters": {
"textBody": "I can reply to text, voice notes, images and PDF documents. Try one of those, or send \"/image\" followed by a description to generate an image.",
"operation": "send",
"phoneNumberId": "={{ $('Configuration').item.json.whatsapp_phone_number_id }}",
"additionalFields": {},
"recipientPhoneNumber": "={{ $('WhatsApp Trigger').item.json.messages[0].from }}"
},
"credentials": {
"whatsAppApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "20fe7a40-292c-40a1-b9cc-13aa6d08827f",
"name": "From audio to audio?",
"type": "n8n-nodes-base.if",
"position": [
2144,
544
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "loose"
},
"combinator": "and",
"conditions": [
{
"id": "c-isaudio",
"operator": {
"type": "object",
"operation": "exists",
"singleValue": true
},
"leftValue": "={{ $('WhatsApp Trigger').item.json.messages[0].audio }}",
"rightValue": ""
},
{
"id": "c-v2v",
"operator": {
"type": "boolean",
"operation": "true",
"singleValue": true
},
"leftValue": "={{ $('Configuration').item.json.reply_voice_to_voice }}",
"rightValue": ""
}
]
}
},
"typeVersion": 2.2
},
{
"id": "e3c3ec46-6327-4791-958a-9745e62299d1",
"name": "Generate Audio Response",
"type": "@n8n/n8n-nodes-langchain.openAi",
"position": [
2352,
496
],
"parameters": {
"input": "={{ $('AI Assistant').item.json.output }}",
"voice": "={{ $('Configuration').item.json.tts_voice }}",
"options": {
"response_format": "mp3",
"binaryPropertyOutput": "data"
},
"resource": "audio"
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 2.3
},
{
"id": "482e5a03-98ad-413a-8186-afe5e2c47669",
"name": "Fix mimeType for Audio",
"type": "n8n-nodes-base.code",
"position": [
2592,
496
],
"parameters": {
"jsCode": "for (const item of $input.all()) {\n if (item.binary) {\n for (const propName of Object.keys(item.binary)) {\n if (item.binary[propName].mimeType === 'audio/mp3') {\n item.binary[propName].mimeType = 'audio/mpeg';\n }\n }\n }\n}\nreturn $input.all();"
},
"typeVersion": 2
},
{
"id": "af14207c-0321-4071-b3a4-168294b70934",
"name": "Send audio",
"type": "n8n-nodes-base.whatsApp",
"position": [
2784,
496
],
"parameters": {
"mediaPath": "useMedian8n",
"operation": "send",
"messageType": "audio",
"phoneNumberId": "={{ $('Configuration').item.json.whatsapp_phone_number_id }}",
"additionalFields": {},
"recipientPhoneNumber": "={{ $('WhatsApp Trigger').item.json.messages[0].from }}"
},
"credentials": {
"whatsAppApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "47bff5b9-0eef-4c5e-a489-8b94fabbd65d",
"name": "Send message",
"type": "n8n-nodes-base.whatsApp",
"position": [
2352,
688
],
"parameters": {
"textBody": "={{ $('AI Assistant').item.json.output }}",
"operation": "send",
"phoneNumberId": "={{ $('Configuration').item.json.whatsapp_phone_number_id }}",
"additionalFields": {},
"recipientPhoneNumber": "={{ $('WhatsApp Trigger').item.json.messages[0].from }}"
},
"credentials": {
"whatsAppApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "ababea52-7096-49fd-ae1a-a658b53deceb",
"name": "Sticky Main",
"type": "n8n-nodes-base.stickyNote",
"position": [
-816,
-464
],
"parameters": {
"color": 4,
"width": 700,
"height": 2000,
"content": "# Run a multimodal WhatsApp AI assistant with text, voice, images, PDFs and image generation\n\n# \ud83d\udce5 [Open full documentation on Notion](https://automatisation.notion.site/Course-Run-a-multimodal-WhatsApp-AI-assistant-with-text-voice-images-PDFs-and-image-generation-39d3d6550fd9817fb911fbd4151ebb3c)\n\nThis workflow turns WhatsApp into a full multimodal AI assistant. It understands text, voice notes, images and PDF documents, keeps short-term memory per contact, and can also **generate an AI image on demand** and send it straight back in the chat.\n\n## How it works\n- **WhatsApp Trigger** receives every incoming message.\n- **Configuration** centralises all the settings you can tweak (command word, image size/quality, voice, etc.).\n- **Input type** (Switch) detects whether the message is text, a voice note, an image or a PDF.\n- **Text** \u2192 if it starts with the image command (default `/image`), it is sent to **Generate image** (DALL\u00b7E) and the picture is returned. Otherwise it goes to the **AI Assistant**.\n- **Voice** \u2192 the audio is downloaded and transcribed (Whisper), then answered by the assistant. If enabled, the reply is returned as a voice note (TTS).\n- **Image** \u2192 the picture is downloaded and described by a vision model, then the assistant answers.\n- **PDF** \u2192 the document text is extracted and summarised/answered by the assistant.\n- **Simple Memory** keeps the last 10 exchanges per contact for natural follow-ups.\n\n## Setup\n1. Create WhatsApp Business Cloud credentials (Meta) and connect the **WhatsApp Trigger** + all WhatsApp send/media nodes.\n2. Create a **Header Auth** credential holding `Authorization: Bearer <your Meta token>` and select it on the 3 **Download** (HTTP Request) nodes \u2014 WhatsApp media URLs need this token.\n3. Connect your **OpenAI** credential on every OpenAI node.\n4. Open **Configuration** and set `whatsapp_phone_number_id` (your Meta phone number ID).\n5. Activate the workflow and set the webhook/callback URL in the Meta dashboard.\n\n## Requirements\n- An n8n instance (Cloud or self-hosted).\n- A WhatsApp Business Cloud account (Meta Developer) with a phone number ID and a permanent access token.\n- An OpenAI API key with access to a chat model, Whisper, TTS and DALL\u00b7E.\n\n## Customization\n- Change the trigger word for images in `image_command` (e.g. `/img`, `/draw`).\n- Adjust `image_size`, `image_quality`, `image_style` for the generated pictures.\n- Change the TTS `tts_voice`, or set `reply_voice_to_voice` to `false` to always answer by text.\n- Swap models directly in the OpenAI nodes (chat model, vision model, DALL\u00b7E, TTS).\n- Edit the assistant persona in the **AI Assistant** system prompt.\n\n---\n\nNeed help customizing?\nContact me for consulting and support : [Linkedin](https://www.linkedin.com/in/doctor-firass/)\n\n# MY NEW YOUTUBE CHANNEL\n\ud83d\udc49 [Subscribe to my new YouTube channel](https://www.youtube.com/@DrFiras_AI). Here I'll share videos and Shorts with practical tutorials and FREE templates for n8n.\n\n[](https://www.youtube.com/@DrFiras_AI)"
},
"typeVersion": 1
},
{
"id": "c593a0cb-4865-462d-bd81-24af9f8e436e",
"name": "Sticky Route",
"type": "n8n-nodes-base.stickyNote",
"position": [
-48,
480
],
"parameters": {
"color": 7,
"width": 680,
"height": 396,
"content": "## 1. Receive & route\nThe WhatsApp Trigger receives the message. **Configuration** holds every setting. **Input type** routes by message type: text, voice, image, PDF, or unsupported."
},
"typeVersion": 1
},
{
"id": "4f0c462a-d899-41ee-baa2-edb9a658c11b",
"name": "Sticky Text",
"type": "n8n-nodes-base.stickyNote",
"position": [
1312,
-400
],
"parameters": {
"color": 7,
"width": 800,
"height": 460,
"content": "## 2. Text & AI image generation\nIf the text starts with the image command (default `/image`), **Generate image** (DALL\u00b7E) creates a picture and **Send image** returns it. Any other text is passed to the AI Assistant."
},
"typeVersion": 1
},
{
"id": "1a3d8c72-7dc5-476f-a5e8-03fe18eaf195",
"name": "Sticky Voice",
"type": "n8n-nodes-base.stickyNote",
"position": [
832,
96
],
"parameters": {
"color": 7,
"width": 880,
"height": 314,
"content": "## 3. Voice \u2192 transcribe\nGet the media URL, download the audio, transcribe it with Whisper, then hand the text to the AI Assistant."
},
"typeVersion": 1
},
{
"id": "fd380370-885c-47d7-9693-57c12a5ef283",
"name": "Sticky Image",
"type": "n8n-nodes-base.stickyNote",
"position": [
832,
416
],
"parameters": {
"color": 7,
"width": 880,
"height": 250,
"content": "## 4. Image \u2192 describe\nGet the media URL, download the image, describe it with a vision model, then hand the description to the AI Assistant."
},
"typeVersion": 1
},
{
"id": "a79c8408-2e2d-4854-975e-07f72d5db365",
"name": "Sticky Document",
"type": "n8n-nodes-base.stickyNote",
"position": [
640,
688
],
"parameters": {
"color": 7,
"width": 1110,
"height": 470,
"content": "## 5. Documents (PDF) & unsupported\nOnly PDFs are accepted: extract the text and pass it to the AI Assistant. Non-PDF files and other unsupported content get a friendly guidance message."
},
"typeVersion": 1
},
{
"id": "8efa506b-90f2-4ffa-b906-2da6b909e670",
"name": "Sticky Reply",
"type": "n8n-nodes-base.stickyNote",
"position": [
1760,
368
],
"parameters": {
"color": 7,
"width": 1190,
"height": 470,
"content": "## 6. AI assistant & reply\nThe AI Assistant (OpenAI Chat Model + Simple Memory) writes the answer. If the original message was a voice note, the reply is converted to speech and sent as audio; otherwise it is sent as text."
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"binaryMode": "separate",
"availableInMCP": true,
"executionOrder": "v1"
},
"versionId": "060570b4-164a-4e05-b3f0-c81550c5ee41",
"nodeGroups": [],
"connections": {
"File": {
"main": [
[
{
"node": "AI Assistant",
"type": "main",
"index": 0
}
]
]
},
"Text": {
"main": [
[
{
"node": "AI Assistant",
"type": "main",
"index": 0
}
]
]
},
"Audio": {
"main": [
[
{
"node": "AI Assistant",
"type": "main",
"index": 0
}
]
]
},
"Image": {
"main": [
[
{
"node": "AI Assistant",
"type": "main",
"index": 0
}
]
]
},
"Input type": {
"main": [
[
{
"node": "Is image request?",
"type": "main",
"index": 0
}
],
[
{
"node": "Get Audio Url",
"type": "main",
"index": 0
}
],
[
{
"node": "Get Image Url",
"type": "main",
"index": 0
}
],
[
{
"node": "Only PDF File",
"type": "main",
"index": 0
}
],
[
{
"node": "Not supported",
"type": "main",
"index": 0
}
]
]
},
"AI Assistant": {
"main": [
[
{
"node": "From audio to audio?",
"type": "main",
"index": 0
}
]
]
},
"Get File Url": {
"main": [
[
{
"node": "Download File",
"type": "main",
"index": 0
}
]
]
},
"Analyze Image": {
"main": [
[
{
"node": "Image",
"type": "main",
"index": 0
}
]
]
},
"Configuration": {
"main": [
[
{
"node": "Input type",
"type": "main",
"index": 0
}
]
]
},
"Download File": {
"main": [
[
{
"node": "Extract from File",
"type": "main",
"index": 0
}
]
]
},
"Get Audio Url": {
"main": [
[
{
"node": "Download Audio",
"type": "main",
"index": 0
}
]
]
},
"Get Image Url": {
"main": [
[
{
"node": "Download Image",
"type": "main",
"index": 0
}
]
]
},
"Only PDF File": {
"main": [
[
{
"node": "Get File Url",
"type": "main",
"index": 0
}
],
[
{
"node": "Incorrect format",
"type": "main",
"index": 0
}
]
]
},
"Simple Memory": {
"ai_memory": [
[
{
"node": "AI Assistant",
"type": "ai_memory",
"index": 0
}
]
]
},
"Download Audio": {
"main": [
[
{
"node": "Transcribe Audio",
"type": "main",
"index": 0
}
]
]
},
"Download Image": {
"main": [
[
{
"node": "Analyze Image",
"type": "main",
"index": 0
}
]
]
},
"Generate image": {
"main": [
[
{
"node": "Send image",
"type": "main",
"index": 0
}
]
]
},
"Transcribe Audio": {
"main": [
[
{
"node": "Audio",
"type": "main",
"index": 0
}
]
]
},
"WhatsApp Trigger": {
"main": [
[
{
"node": "Configuration",
"type": "main",
"index": 0
}
]
]
},
"Extract from File": {
"main": [
[
{
"node": "File",
"type": "main",
"index": 0
}
]
]
},
"Is image request?": {
"main": [
[
{
"node": "Generate image",
"type": "main",
"index": 0
}
],
[
{
"node": "Text",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Assistant",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"From audio to audio?": {
"main": [
[
{
"node": "Generate Audio Response",
"type": "main",
"index": 0
}
],
[
{
"node": "Send message",
"type": "main",
"index": 0
}
]
]
},
"Fix mimeType for Audio": {
"main": [
[
{
"node": "Send audio",
"type": "main",
"index": 0
}
]
]
},
"Generate Audio Response": {
"main": [
[
{
"node": "Fix mimeType for Audio",
"type": "main",
"index": 0
}
]
]
}
}
}
Credentials you'll need
Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.
openAiApiwhatsAppApiwhatsAppTriggerApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
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. Triggers when a new WhatsApp message is…
Source: https://n8n.io/workflows/17216/ — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
Transform your salon/service business with this streamlined WhatsApp automation system featuring Claude integration, zero-setup database management, and intelligent conversation handling. Claude MCP I
WhatsApp Trigger, WhatsApp, Redis +11
48_WAgentEnhancement. Uses whatsAppTrigger, whatsApp, openAi, httpRequest. Event-driven trigger; 56 nodes.
WhatsApp Trigger, WhatsApp, OpenAI +13
This workflow creates a complete AI-powered restaurant ordering system through WhatsApp. It receives customer messages, processes multimedia content (text, voice, images, PDFs, location), uses GPT-4 t
OpenAI Chat, Memory Postgres Chat, HTTP Request +6
This template is designed for anyone who wants to use WhatsApp as a personal AI assistant hub. If you often juggle tasks, emails, calendars, and expenses across multiple tools, this workflow consolida
OpenAI Chat, Memory Buffer Window, Mcp Client Tool +12
⚠️ EDUCATIONAL DEMONSTRATION ONLY - NOT FOR PRODUCTION MEDICAL USE ⚠️
Agent, Memory Postgres Chat, OpenAI Chat +7