AI Agents
Build intelligent voice conversations with OpenAI and Google Gemini
15 nodes
309
192
Webhook
Workflow Description
Automation that receives voice requests via Webhook, preserves conversation context in memory, and routes dialogues to OpenAI or Google Gemini for intelligent processing and instant responses.
How it works
- 1.Receive voice requests via Webhook and identify which language model to use
- 2.Store conversation history in memory while managing context window for optimal performance
- 3.Route messages to OpenAI or Google Gemini based on configured preferences
- 4.Process responses and format them for immediate delivery
- 5.Send results back via Webhook while maintaining conversation continuity
Use cases
- Customer support application that answers voice inquiries automatically
- Virtual assistant that remembers context across multiple user interactions
- Interactive system delivering natural-sounding responses to frequently asked questions
Requirements
- API keys from both OpenAI and Google Cloud for authentication
- Active Webhook endpoint capable of receiving HTTP POST requests
- Ability to handle voice inputs and process complex text responses
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
309
Downloads
192
How to Use
- 1.Click "Download Template"
- 2.Open your n8n dashboard
- 3.Go to Workflows > Import from File
- 4.Select downloaded file and configure credentials
Nodes Used (15)
/
Get Chat
Memory Manager
Insert Chat
Memory Manager
Sticky Note5
Sticky Note
Sticky Note
Sticky Note
Aggregate
Aggregate
Window Buffer Memory
Memory Buffer Window
Google Gemini Chat Model
Gemini Model
Respond to Webhook
Webhook
ElevenLabs - Generate Audio
HTTP Request
Sticky Note2
Sticky Note
Sticky Note1
Sticky Note
Limit
Limit
Basic LLM Chain
LLM Chain
Webhook
Webhook
OpenAI - Speech to Text
OpenAI