# Summarize Zoom meetings with OpenAI and Whisper: n8n workflow

> Started by another system calling it, and works across Gmail and Supabase vectors. It puts OpenAI behind a retrieval step, so answers are drawn from...

Source: https://millionrounds.com/workflow/summarize-zoom-meetings-with-openai-and-whisper (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Scheduling](https://millionrounds.com/workflows?category=Scheduling#library)

# Summarize Zoom meetings with OpenAI and Whisper

Started by another system calling it, and works across Gmail and Supabase vectors. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 19 steps, 1 branch: a working afternoon to understand properly.

Medium Calls a model: OpenAI Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fsummarize-zoom-meetings-with-openai-and-whisper)

**19 steps** Medium: a working afternoon

**1** Branch: places the flow splits

**0** Loops or waits

**2** Services it connects to

## The flow

Starts it 1 Model 9 Logic 6 Service 3

The steps in the order they run, from what starts it.

- 1 **Zoom Meeting Trigger (Recording Webhook)** Webhook *Starts it*
- 2 **GPT-4o Reasoning Model** Lm Chat Open Ai *Model*
- 3 **AI Response Validator (JSON Enforcer)** Output Parser Structured *Model*
- 4 **Semantic Embedding Generator** Embeddings Open Ai *Model*
- 5 **Metadata Attachment Engine** Document Default Data Loader *Model*
- 6 **Vector Embedding Generator1** Embeddings Open Ai *Model*
- 7 **Meeting Payload Parser** Set *Logic*
- 8 **Meeting Intelligence Engine (LLM Processor)** Agent *Model*
- 9 **Historical Meeting Search Engine (RAG Retriever)** Vector Store Supabase *Model*
- 10 **Meeting Memory Storage (Vector DB Insert)** Vector Store Supabase *Model*
- 11 **Audio File Downloader (Zoom Cloud Fetch)** Http Request *Service*
- 12 **Transcript Fingerprint Generator** Code *Logic*
- 13 **Meeting Summary Email Dispatcher** Gmail *Service*
- 14 **Audio Transcription (OpenAI Whisper)** Open Ai *Model*
- 15 **Supabase Duplicate Check Query** Http Request *Service*
- 16 **Transcript Normalizer** Code *Logic*
- 17 **Duplicate Result Analyzer** Code *Logic*
- 18 **Duplicate Gate Controller** If *Logic*
- 19 **Structured Memory Builder** Code *Logic*

## How it's built

- **Starts on:** Another system calling it
- **Steps:** 19, with 1 branch
- **Size:** Medium: a working afternoon
- **Connects to:** Gmail, Supabase vectors
- **Model:** OpenAI
- **Retrieval:** Answers are drawn from documents you supply, not from the model alone

## Questions

What does it need to run?

An n8n account, plus your own Gmail and Supabase vectors accounts, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on another system calling it.

Does it use AI?

Yes. It calls OpenAI. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Plan an afternoon. 19 steps is enough that you should read each one before running it.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

**Before you run it**

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 19 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fsummarize-zoom-meetings-with-openai-and-whisper)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Connects to

Each opens the other workflows that use it.

[Gmail](https://millionrounds.com/workflows?service=Gmail#library)[Supabase vectors](https://millionrounds.com/workflows?service=Supabase+vectors#library)

## Workflows like it

Also scheduling, with the same services where possible, closest in size first.

- [**Automate email triage & meeting scheduling with Gmail** 19 steps · calls a model · Gmail, Google Calendar](https://millionrounds.com/workflow/automate-email-triage-and-meeting-scheduling-with-gmail)
- [**Handle meeting no-shows with Gmail and Google Calendar** 19 steps · calls a model · Gmail, Google Calendar](https://millionrounds.com/workflow/handle-meeting-no-shows-with-gmail-and-google-calendar)
- [**Organize school emails with Google Calendar and Drive** 19 steps · calls a model · Gmail, Google Calendar](https://millionrounds.com/workflow/organize-school-emails-with-google-calendar-and-drive)
- [**Qualifying appointment requests with OpenAI and Gmail** 19 steps · calls a model · Gmail, Google Calendar](https://millionrounds.com/workflow/qualifying-appointment-requests-with-openai-and-gmail)
- [**Triage and schedule healthcare appointments with Azure OpenAI** 19 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/triage-and-schedule-healthcare-appointments-with-azure-opena)
- [**Auto-generate sales meeting briefs with OpenAI and LinkedIn** 18 steps · calls a model · Gmail, Google Calendar](https://millionrounds.com/workflow/auto-generate-sales-meeting-briefs-with-openai-and-linkedin)