OpenAI: GPT-4o Transcribe

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.

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)

Related models

Whisper Large v3 Turbo

Voxtral Mini Transcribe

Nemotron 3.5 ASR Streaming 0.6B

GPT-4o Mini Transcribe