How to beginner · 3 min read

Whisper API pricing

Q: Whisper API pricing

The Whisper API by OpenAI charges per minute of audio processed, with pricing starting at $0.006 per minute for the whisper-1 model. This pay-as-you-go model applies to all audio transcription and translation requests via the API.

Quick answer

The Whisper API by OpenAI charges per minute of audio processed, with pricing starting at $0.006 per minute for the whisper-1 model. This pay-as-you-go model applies to all audio transcription and translation requests via the API.

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.

bash

pip install openai>=1.0

Step by step

Use the Whisper API to transcribe an audio file with the whisper-1 model. Pricing is based on the audio length in minutes.

python

import os
from openai import OpenAI

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

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

print(transcript.text)

output

Transcribed text from the audio file.

Common variations

You can also use the Whisper API for translation by changing the method to audio.translations.create. Pricing remains per minute of audio processed. Async usage or streaming is not currently supported for Whisper.

python

with open("audio.mp3", "rb") as audio_file:
    translation = client.audio.translations.create(
        model="whisper-1",
        file=audio_file
    )

print(translation.text)

output

Translated text from the audio file.

Pricing details

OpenAI charges $0.006 per minute of audio processed with the whisper-1 model. There are no additional fees for usage. Pricing is subject to change; always check the official pricing page.

Model	Price per minute (USD)
whisper-1	$0.006

✅

Key Takeaways

Use the whisper-1 model for cost-effective audio transcription at $0.006 per minute.
Pricing is strictly per minute of audio processed, with no hidden fees.
The openai Python SDK supports simple synchronous transcription and translation calls.
Always set your API key securely via environment variables for authentication.
Check OpenAI's official pricing page regularly for updates.

Verified 2026-04 · whisper-1

Verify ↗