GPT Audio

import base64
from pathlib import Path
from openai import OpenAI

client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.mixroute.ai/v1")

response = client.chat.completions.create(
    model="gpt-audio",
    modalities=["text", "audio"],
    audio={"voice": "alloy", "format": "wav"},
    messages=[{"role": "user", "content": "Give a short spoken welcome to MixRoute."}],
    max_completion_tokens=256,
)

audio = response.choices[0].message.audio
Path("reply.wav").write_bytes(base64.b64decode(audio.data))
print(audio.transcript)