How to beginner · 3 min read

How to transcribe audio with OpenAI Whisper API

Q: How to transcribe audio with OpenAI Whisper API

Use the OpenAI Whisper API by calling client.audio.transcriptions.create with your audio file and model="whisper-1". This returns a transcription text from the audio input. Authenticate with your OpenAI API key and provide supported audio formats like mp3 or wav.

Quick answer

Use the OpenAI Whisper API by calling client.audio.transcriptions.create with your audio file and model="whisper-1". This returns a transcription text from the audio input. Authenticate with your OpenAI API key and provide supported audio formats like mp3 or wav.

PREREQUISITES

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

Setup

Install the official OpenAI Python SDK and set your API key as an environment variable.

Install SDK: pip install openai
Set API key in your shell: export OPENAI_API_KEY='your_api_key' (Linux/macOS) or setx OPENAI_API_KEY "your_api_key" (Windows)

bash

pip install openai

Step by step

This example demonstrates how to transcribe an audio file using the OpenAI Whisper API with the whisper-1 model. Supported audio formats include mp3, wav, m4a, and more.

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.mp3"

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

print("Transcription:", transcript.text)

output

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

Common variations

Async usage: Use an async client and await the transcription call.
Different audio formats: Whisper supports mp3, mp4, mpeg, mpga, m4a, wav, webm.
Local transcription: Use the openai-whisper Python package for offline transcription.

python

import asyncio
import os
from openai import OpenAI

async def transcribe_async():
    client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
    with open("audio.mp3", "rb") as audio_file:
        transcript = await client.audio.transcriptions.acreate(
            model="whisper-1",
            file=audio_file
        )
    print("Async transcription:", transcript.text)

asyncio.run(transcribe_async())

output

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

Troubleshooting

If you get Invalid file format, ensure your audio file is one of the supported formats and not corrupted.
If transcription is inaccurate, try using higher quality audio or a different Whisper model if available.
For AuthenticationError, verify your OPENAI_API_KEY environment variable is set correctly.

✅

Key Takeaways

Use client.audio.transcriptions.create with model="whisper-1" to transcribe audio files via OpenAI API.
Supported audio formats include mp3, wav, m4a, mp4, and webm; file size limit is 25MB for API calls.
Set your OpenAI API key in the environment variable OPENAI_API_KEY before running code.
Async transcription is supported with acreate method for integration in async apps.
For local offline transcription, use the openai-whisper Python package instead of the API.

Verified 2026-04 · whisper-1

Verify ↗