How to Intermediate · 4 min read

Earnings call analysis with LLM

Q: Earnings call analysis with LLM

Use a large language model like gpt-4o to analyze earnings call transcripts by feeding the transcript text as input and prompting for summary, sentiment, or key insights. The OpenAI Python SDK enables easy integration for extracting financial insights from calls.

Quick answer

Use a large language model like gpt-4o to analyze earnings call transcripts by feeding the transcript text as input and prompting for summary, sentiment, or key insights. The OpenAI Python SDK enables easy integration for extracting financial insights from calls.

PREREQUISITES

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

Setup

Install the openai Python package and set your API key as an environment variable for secure access.

bash

pip install openai>=1.0

output

Collecting openai
  Downloading openai-1.x.x-py3-none-any.whl (xx kB)
Installing collected packages: openai
Successfully installed openai-1.x.x

Step by step

This example loads an earnings call transcript, sends it to gpt-4o with a prompt to summarize key financial highlights, and prints the output.

python

import os
from openai import OpenAI

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

transcript = '''
Good morning everyone, and thank you for joining our Q1 earnings call. This quarter, revenue grew 12% year-over-year driven by strong demand in our cloud services segment. Operating margin improved by 3 percentage points due to cost efficiencies. We raised our full-year guidance reflecting this momentum.
'''

prompt = f"Analyze the following earnings call transcript and summarize the key financial highlights:\n\n{transcript}\n\nSummary:" 

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

print("Earnings call summary:")
print(response.choices[0].message.content)

output

Earnings call summary:
The company reported a 12% year-over-year revenue growth driven by cloud services, improved operating margin by 3 percentage points due to cost efficiencies, and raised full-year guidance based on strong momentum.

Common variations

Use gpt-4o-mini for faster, lower-cost analysis with slightly less detail.
Implement async calls with asyncio for concurrent transcript processing.
Stream partial results using stream=True in chat.completions.create for real-time analysis feedback.

python

import os
import asyncio
from openai import OpenAI

async def analyze_transcript_async(transcript: str):
    client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
    prompt = f"Summarize key financial points from this earnings call:\n\n{transcript}\n\nSummary:"
    response = await client.chat.completions.create(
        model="gpt-4o-mini",
        messages=[{"role": "user", "content": prompt}]
    )
    print("Async summary:", response.choices[0].message.content)

asyncio.run(analyze_transcript_async("Sample transcript text here."))

output

Async summary: The earnings call highlighted revenue growth, margin improvement, and raised guidance reflecting positive business trends.

Troubleshooting

If you receive RateLimitError, reduce request frequency or upgrade your API plan.
For InvalidRequestError due to input length, chunk the transcript into smaller parts before sending.
Ensure your OPENAI_API_KEY environment variable is set correctly to avoid authentication errors.

✅

Key Takeaways

Use gpt-4o for detailed earnings call analysis and gpt-4o-mini for cost-effective summaries.
Chunk large transcripts to fit model context windows and avoid input length errors.
Async and streaming calls enable scalable and real-time earnings call processing.
Always secure your API key via environment variables to prevent leaks.

Verified 2026-04 · gpt-4o, gpt-4o-mini

Verify ↗