Intelligent AI Voice Chat with Conversational Memory
detail.loadingPreview
This n8n workflow powers an intelligent AI voice chat experience, seamlessly integrating speech-to-text, advanced language models (Google Gemini), conversational memory, and high-quality text-to-speech (ElevenLabs) to create dynamic and context-aware voice interactions.
About This Workflow
Unlock the potential of conversational AI with this powerful n8n workflow designed to create an intelligent voice chat assistant. It starts by listening for incoming voice messages via a webhook, then leverages an assumed OpenAI Speech-to-Text node to transcribe audio into text. The workflow intelligently manages conversation history using LangChain's Memory Manager nodes, ensuring your AI maintains context across interactions. Google Gemini processes the user's query and context to generate a thoughtful response, which is then transformed into natural-sounding speech by ElevenLabs. Finally, the generated audio is returned, completing a real-time, engaging voice conversation. This full-stack AI voice solution is perfect for building interactive voice applications.
Key Features
- Real-time Voice Interaction: Initiate and receive AI responses instantly via a webhook, enabling dynamic voice conversations.
- Conversational Memory: Utilizes LangChain's Memory Manager and Window Buffer to retain context throughout the chat, ensuring coherent and personalized interactions.
- Advanced LLM Integration: Employs the Google Gemini 1.5 Flash model for highly intelligent and relevant text generation based on user input and conversation history.
- High-Quality Text-to-Speech: Integrates with ElevenLabs via an HTTP Request node to convert AI-generated text into natural, expressive speech, enhancing the user experience.
- Flexible AI Choice: While using ElevenLabs for TTS, the workflow also notes the option to use OpenAI's audio generation, offering flexibility in your AI toolkit.
How To Use
- Configure the Webhook: Set up the "Webhook" node (path:
/voice_message) to listen for incoming voice message triggers from your application or system. - Set up Google Gemini: Provide your Google Gemini API credentials in the "Google Gemini Chat Model" node. The workflow is pre-configured to use
models/gemini-1.5-flash. - Integrate ElevenLabs (HTTP Request):
- Get API Key and Voice ID: Obtain your ElevenLabs API Key and a desired Voice ID from the ElevenLabs website.
- Update URL: In the "ElevenLabs - Generate Audio" node, replace
{{voice id}}at the end of the URL with your actual Voice ID. - Custom Authentication: Configure custom authentication in the "ElevenLabs - Generate Audio" node. Add a header
xi-api-keywith your ElevenLabs API Key as its value.
- Speech-to-Text Integration: Ensure you have an upstream node (e.g., an OpenAI Speech-to-Text node, not shown in the snippet but referenced) configured to transcribe incoming audio into text for the LLM to process.
- Activate Workflow: Once all credentials and configurations are set, activate the workflow to enable your intelligent AI voice chat.
Apps Used
Workflow JSON
{
"id": "14621a8a-50b3-4a7e-aa4f-e4304c995127",
"name": "Intelligent AI Voice Chat with Conversational Memory",
"nodes": 16,
"category": "Operations",
"status": "active",
"version": "1.0.0"
}Note: This is a sample preview. The full workflow JSON contains node configurations, credentials placeholders, and execution logic.
Get This Workflow
ID: 14621a8a-50b3...
About the Author
SaaS_Connector
Integration Guru
Connecting CRM, Notion, and Slack to automate your life.
Statistics
Related Workflows
Discover more workflows you might like
Google Sheets to Icypeas: Automated Bulk Domain Scanning
This workflow streamlines the process of performing bulk domain scans by integrating your Google Sheets data directly with the Icypeas platform. Automate the submission of company names from your spreadsheet to Icypeas for comprehensive domain information, saving valuable time and effort.
Instant WooCommerce Order Notifications via Telegram
When a new order is placed on your WooCommerce store, instantly receive detailed notifications directly to your Telegram chat. Stay on top of your e-commerce operations with real-time alerts, including order specifics and a direct link to view the order.
On-Demand Microsoft SQL Query Execution
This workflow allows you to manually trigger and execute any SQL query against your Microsoft SQL Server database. Perfect for ad-hoc data lookups, administrative tasks, or quick tests, giving you direct control over your database operations.