How to beginner · 3 min read

How to transcribe audio with OpenAI in python

Q: How to transcribe audio with OpenAI in python

Use the OpenAI Python SDK's client.audio.transcriptions.create method with your audio file and model (e.g., whisper-1) to transcribe audio to text. Provide the audio file as a binary stream and specify the model to get the transcription result.

Quick answer

Use the OpenAI Python SDK's client.audio.transcriptions.create method with your audio file and model (e.g., whisper-1) to transcribe audio to text. Provide the audio file as a binary stream and specify the model to get the transcription result.

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 for secure authentication.

bash

pip install openai>=1.0

Step by step

This example demonstrates how to transcribe an audio file (e.g., WAV or MP3) using OpenAI's Whisper model whisper-1. The audio file is read in binary mode and sent to the audio.transcriptions.create endpoint.

python

import os
from openai import OpenAI

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

# Path to your audio file
audio_file_path = "audio_sample.wav"

with open(audio_file_path, "rb") as audio_file:
    transcription = client.audio.transcriptions.create(
        file=audio_file,
        model="whisper-1"
    )

print("Transcription:", transcription.text)

output

Transcription: Hello, this is a sample audio transcription using OpenAI Whisper.

Common variations

Use different audio formats supported by Whisper such as MP3, MP4, or FLAC.
Specify the language parameter to improve accuracy for known languages.
Use asynchronous calls or integrate with frameworks for streaming audio transcription.

python

import os
from openai import OpenAI

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

with open("audio_sample.mp3", "rb") as audio_file:
    transcription = client.audio.transcriptions.create(
        file=audio_file,
        model="whisper-1",
        language="en"
    )

print("Transcription:", transcription.text)

output

Transcription: This is an English audio transcription example.

Troubleshooting

If you get a FileNotFoundError, verify the audio file path is correct.
If the transcription is empty or inaccurate, check the audio quality and format.
Ensure your API key is set correctly in the environment variable OPENAI_API_KEY.
For large files, consider chunking or using streaming transcription if supported.

✅

Key Takeaways

Use client.audio.transcriptions.create with whisper-1 to transcribe audio files.
Always read audio files in binary mode and pass the file object to the API.
Set the language parameter to improve transcription accuracy when known.
Verify your environment variable OPENAI_API_KEY is correctly set before running code.
Check audio format compatibility and file path correctness to avoid common errors.

Verified 2026-04 · whisper-1

Verify ↗