AI Agents

Build intelligent voice conversations with dual AI models

15 nodes 283 126 Webhook
Download

Workflow Description

Automation that receives voice requests via webhook and processes them using OpenAI and Google Gemini models, maintaining conversation context in memory to ensure coherent and contextually aware responses throughout extended dialogues.

How it works

  1. 1.Receive voice request via webhook and identify the sender
  2. 2.Store previous conversation context in memory manager
  3. 3.Process text through LLM chain and route to optimal AI model
  4. 4.Generate response from OpenAI or Gemini based on context
  5. 5.Send processed reply back via webhook to the client

Use cases

  • Self-service customer support with context-aware sequential conversations
  • Intelligent assistant chatbots that retain memory of extended interactions

Requirements

  • Valid API keys for OpenAI and Google Gemini
  • Configured webhook endpoint to receive voice requests
  • Sufficient memory capacity to store multiple conversation contexts

Service Value

Ideal as a smart automation service combining integrations and AI to produce ready-to-use results.

Apps Used

Memory Gemini LLM Chain OpenAI

Details

Trigger Webhook
Nodes 15
Apps 4
Views 283
Downloads 126

How to Use

  1. 1.Click "Download Template"
  2. 2.Open your n8n dashboard
  3. 3.Go to Workflows > Import from File
  4. 4.Select downloaded file and configure credentials

Nodes Used (15)

/

Get Chat

Memory Manager

#1

Insert Chat

Memory Manager

#2

Sticky Note5

Sticky Note

#3

Sticky Note

Sticky Note

#4

Aggregate

Aggregate

#5

Window Buffer Memory

Memory Buffer Window

#6

Google Gemini Chat Model

Gemini Model

#7

Respond to Webhook

Webhook

#8

ElevenLabs - Generate Audio

HTTP Request

#9

Sticky Note2

Sticky Note

#10

Sticky Note1

Sticky Note

#11

Limit

Limit

#12

Basic LLM Chain

LLM Chain

#13

Webhook

Webhook

#14

OpenAI - Speech to Text

OpenAI

#15