How to beginner · 3 min read

How to use AI to summarize meeting transcripts

Q: How to use AI to summarize meeting transcripts

Use a large language model like gpt-4o to process meeting transcripts by sending the transcript text as input and requesting a concise summary via the chat.completions.create API. This approach extracts key points and action items efficiently from raw transcript data.

Quick answer

Use a large language model like gpt-4o to process meeting transcripts by sending the transcript text as input and requesting a concise summary via the chat.completions.create API. This approach extracts key points and action items efficiently from raw transcript data.

PREREQUISITES

Python 3.8+
OpenAI API key (free tier works)
pip install openai>=1.0

Setup

Install the OpenAI Python SDK and set your API key as an environment variable to authenticate requests.

bash

pip install openai>=1.0

Step by step

Use the gpt-4o model to summarize a meeting transcript by sending the transcript text in a user message and prompting the model to generate a concise summary.

python

import os
from openai import OpenAI

client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

transcript = '''
John: Let's start the project timeline discussion.
Mary: We need to finalize the budget by next week.
John: Agreed, and assign tasks by Friday.
Mary: I'll prepare the draft proposal.
'''

prompt = f"Summarize the following meeting transcript with key points and action items:\n\n{transcript}"

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": prompt}]
)

summary = response.choices[0].message.content
print("Meeting Summary:\n", summary)

output

Meeting Summary:
- Discussed project timeline.
- Budget finalization due next week.
- Task assignments by Friday.
- Draft proposal to be prepared by Mary.

Common variations

You can use asynchronous calls for better performance or try other models like claude-3-5-sonnet-20241022 for potentially improved summarization quality. Streaming responses can also be used for real-time summary generation.

python

import asyncio
import os
from openai import OpenAI

async def async_summarize(transcript: str):
    client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
    prompt = f"Summarize the following meeting transcript with key points and action items:\n\n{transcript}"
    response = await client.chat.completions.acreate(
        model="gpt-4o",
        messages=[{"role": "user", "content": prompt}]
    )
    print("Async Meeting Summary:\n", response.choices[0].message.content)

transcript = '''
John: Let's start the project timeline discussion.
Mary: We need to finalize the budget by next week.
John: Agreed, and assign tasks by Friday.
Mary: I'll prepare the draft proposal.
'''

asyncio.run(async_summarize(transcript))

output

Async Meeting Summary:
- Discussed project timeline.
- Budget finalization due next week.
- Task assignments by Friday.
- Draft proposal to be prepared by Mary.

Troubleshooting

If the summary is too long or unfocused, add instructions to limit length or focus on action items in the prompt.
If you get rate limit errors, reduce request frequency or upgrade your API plan.
For very long transcripts, split them into chunks and summarize each separately before combining.

✅

Key Takeaways

Use gpt-4o with clear prompts to extract concise meeting summaries.
Manage long transcripts by chunking to avoid token limits.
Async and streaming APIs improve responsiveness for large inputs.

Verified 2026-04 · gpt-4o, claude-3-5-sonnet-20241022

Verify ↗