Automatically generate action items from a meeting with LeMUR
In this guide, you’ll learn how to use AssemblyAI to process an audio file and then automatically generate action items from the meeting’s transcript.
Overview
Before we begin, make sure you have an AssemblyAI account and an API key. You can sign up for an AssemblyAI account and get your API key from your dashboard.
LeMUR features are currently only available to paid users at two pricing tiers, LeMUR Default and LeMUR Basic. Refer to our pricing page for more detail.
Step-by-step instructions
In this guide, you’ll use AssemblyAI to transcribe a meeting recording. Then, you’ll request a list of action items from LeMUR.
-
1
Create a new file and import the necessary libraries. Configure an authenticated HTTP request using your API key.
-
2
Upload your local file to the AssemblyAI API.
-
3
Submit a transcription with the
audio_url
parameter set to the value ofupload_url
. -
4
After making the request, you’ll receive an ID for the transcription. Use it to poll the API every few seconds to check the status of the transcript job. Once the status is
completed
, you can retrieve the transcript from the API response. -
5
Define a prompt to tell LeMUR to extract action items from this meeting.
-
6
Create a JSON payload containing the transcript ID and your
prompt
as part of a POST request to the LeMUR Task endpoint.
Understanding the response
The result of your LeMUR output should be something like this: