This workflow follows the Agent → OpenAI Chat 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 →
{
"name": "Mario Speaker",
"nodes": [
{
"parameters": {
"resource": "audio",
"operation": "transcribe",
"binaryPropertyName": "file0",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.openAi",
"typeVersion": 1.8,
"position": [
320,
-176
],
"id": "97d65a7e-2eab-4c5c-9520-8fb264fffc9e",
"name": "OpenAI",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "a897cbf4-f60a-493f-814d-75093074c478",
"name": "conversation",
"value": "={{ $json.output }}",
"type": "string"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
1024,
-64
],
"id": "08341bc6-6156-40ba-a1da-bee76e1bf8e2",
"name": "formatToLLM1"
},
{
"parameters": {
"httpMethod": "POST",
"path": "948e960f-5467-4126-9bf2-3d9e8b8e26a7",
"responseMode": "responseNode",
"options": {
"binaryPropertyName": "file"
}
},
"type": "n8n-nodes-base.webhook",
"typeVersion": 2.1,
"position": [
-320,
-176
],
"id": "0627547f-5b88-4e86-9d84-1b666ca16c3e",
"name": "Webhook"
},
{
"parameters": {
"respondWith": "allIncomingItems",
"options": {}
},
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.4,
"position": [
1280,
-176
],
"id": "14b2822e-fa29-49cd-a05f-0d4a5f5d6005",
"name": "Respond to Webhook"
},
{
"parameters": {
"promptType": "define",
"text": "={{ $json.text }}",
"options": {
"systemMessage": "Voc\u00ea \u00e9 o Mario Bros, fale como ele e quero respostas muito curtas e sem emojis ou caracteres especiais, mas pode usar pontua\u00e7\u00e3o para dar emo\u00e7\u00e3o na fala. Lembra que vou ler em voz alta pro humano. "
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 2.2,
"position": [
640,
-192
],
"id": "bd960657-0c1d-4e52-9edd-df0e70ac29fd",
"name": "AI Agent"
},
{
"parameters": {
"model": {
"__rl": true,
"value": "gpt-4o-mini",
"mode": "list",
"cachedResultName": "gpt-4o-mini"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1.2,
"position": [
640,
32
],
"id": "ffae52be-9d3b-49f0-93cb-b7079d9bd1b6",
"name": "OpenAI Chat Model",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"sessionIdType": "customKey",
"sessionKey": "1"
},
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"typeVersion": 1.3,
"position": [
816,
176
],
"id": "73c1764c-af27-4fe2-b183-7dacebb7f0bd",
"name": "Simple Memory"
}
],
"connections": {
"OpenAI": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"Webhook": {
"main": [
[
{
"node": "OpenAI",
"type": "main",
"index": 0
}
]
]
},
"formatToLLM1": {
"main": [
[
{
"node": "Respond to Webhook",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Simple Memory": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"AI Agent": {
"main": [
[
{
"node": "formatToLLM1",
"type": "main",
"index": 0
}
]
]
}
},
"active": true,
"settings": {
"executionOrder": "v1"
},
"versionId": "c9ab0c3b-c504-48c7-9231-bc5ff543253c",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "fbEihV5aq7GIzJdt",
"tags": []
}
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.
openAiApi
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Mario Speaker. Uses openAi, agent, lmChatOpenAi, memoryBufferWindow. Webhook trigger; 7 nodes.
Source: https://github.com/gustavocp/mario-speaker/blob/00bd4e1bc1ec5198fb740541ed0c7134f5c303f3/n8n/MarioSpeakerWorkflow.json — 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.
VEP WAPP. Uses openAi, lmChatOpenAi, toolCalculator, agent. Webhook trigger; 100 nodes.
Aura-bot. Uses postgres, lmChatOpenAi, memoryBufferWindow, httpRequest. Webhook trigger; 82 nodes.
My workflow 15. Uses httpRequest, memoryBufferWindow, agent, lmChatOpenAi. Webhook trigger; 74 nodes.
1-[Agente-Abogado]-Asistente-Whatsapp. Uses lmChatOpenAi, toolWorkflow, toolCalculator, agent. Webhook trigger; 52 nodes.
All-in-One Telegram/Baserow AI Assistant 🤖🧠 Voice/Photo/Save Notes/Long Term Mem. Uses stickyNote, lmChatOpenAi, telegram, agent. Webhook trigger; 48 nodes.