← All models
OpenAI: GPT-4o Transcribe
openai/gpt-4o-transcribetranscription
GPT-4o Transcribe is OpenAI's high-quality speech-to-text model built on GPT-4o audio capabilities. It's priced per token (input and output), making it suitable for workflows that benefit from token-level billing transparency.
Price in / out
Context
128K
Released
Apr 27, 2026
Parameters
fileaudio file (multipart)How to use via API
from openai import OpenAI
client = OpenAI(base_url="https://api.mixen.ai/v1", api_key="mxn-...")
tr = client.audio.transcriptions.create(
model="openai/gpt-4o-transcribe",
file=open("audio.mp3", "rb"),
)
print(tr.text)
