Ask questions about past meetings using voice with OpenAI and Pinecone
Ready for 3.0Ready for 3.0. This template uses no nodes that n8n 3.0 removes. No removed nodes, versions or helpers found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 11 nodes and runs when an HTTP POST request hits its webhook URL. Along the way it connects OpenAI, Embeddings OpenAI, Pinecone Vector Store and Azure OpenAI Chat Model.
How it runs
Trigger: When an HTTP POST request hits its webhook URL.
- Transcribe Voice Question (OpenAI): transcribe (audio)
- Extract Voice Question (Code): runs custom JavaScript code
- Search Meetings in Pinecone (Pinecone Vector Store): searches the Pinecone vector store, with embeddings: Generate Question Embedding
- Build Meeting Context (Code): runs custom JavaScript code
- Answer Question from Meetings (AI Agent): runs an AI agent, with model: AI Chat Model
- Prepare Answer for Audio (Code): runs custom JavaScript code
- Generate Spoken Answer (OpenAI): work with audio
- Return Audio Response (Respond to Webhook): sends the response back to the webhook caller
Services it uses
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (8)
- Webhook
n8n-nodes-base.webhook - OpenAI
@n8n/n8n-nodes-langchain.openAi - Code
n8n-nodes-base.code - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Pinecone Vector Store
@n8n/n8n-nodes-langchain.vectorStorePinecone - AI Agent
@n8n/n8n-nodes-langchain.agent - Azure OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatAzureOpenAi - Respond to Webhook
n8n-nodes-base.respondToWebhook
From the author
📊 Description This workflow allows users to ask questions about past meetings using their voice. It converts the voice question into text, searches stored meeting notes using Pinecone, and replies with a spoken answer generated by AI. It helps teams quickly…