Automating Meeting Notes with Microsoft Graph API and Azure OpenAI – Part 1

Microsoft 365 Copilot offers powerful AI-driven meeting note generation, but its licensing costs can be a significant investment for organizations. For those looking for a more cost-effective alternative, leveraging Power Automate with Microsoft Graph API and Azure OpenAI provides a scalable and budget-friendly solution. In this series, we will walk through how to automate the process of generating meeting notes by retrieving transcriptions via the Microsoft Graph API and summarizing them with Azure OpenAI’s language models.

Retrieving Meeting Transcriptions with Microsoft Graph API

To start, we need to extract meeting transcriptions from Microsoft Teams using Microsoft Graph API. Microsoft provides an endpoint for accessing recorded meeting transcriptions, but there are specific permissions and configurations required.

Prerequisites

Before proceeding, ensure that you have:

• Access to Microsoft Graph API with the appropriate permissions.
• An Azure Active Directory (Entra ID) app registration with delegated permissions.
• Power Automate with premium connectors enabled.
• An Azure OpenAI service instance for text processing.

Step 1: Set Up Permissions in Azure AD

1. Navigate to Microsoft Entra ID.
2. Create a new App Registration and note the Application (Client) ID and Tenant ID.
3. Under API Permissions, add the following permissions:
   • OnlineMeetings.Read.All (Delegated)
   • TeamsTranscripts.Read.All (Delegated)
4. Grant admin consent to apply the permissions.

Step 2: Retrieve Transcriptions Using Power Automate

1. Open Power Automate and create a new Instant Cloud Flow.
2. Use the HTTP with Azure AD connector to call the Microsoft Graph API endpoint:

GET https://graph.microsoft.com/v1.0/me/onlineMeetings/{meetingId}/transcripts

• Parse the JSON response to extract the transcription text.

Step 3: Store Transcription Data

To keep track of transcriptions, store them in a SharePoint list, Dataverse, or any storage service for further processing.

Next Steps

In Part 2, we will integrate Azure OpenAI’s GPT model to summarize the transcription and generate structured meeting notes. Stay tuned!

Do you like this article?

Subscribe to my blog with your email address using the widget on the right side or on the bottom of this page to have new articles sent directly to your inbox the moment I publish them.

Original Post https://ashiqf.com/2025/02/28/automating-meeting-notes-with-microsoft-graph-api-and-azure-openai-part-1/