Audio Understanding

from openai import OpenAI
import base64

client = OpenAI(
    api_key="your_mimo_api_key",
    base_url="https://api.mimo-v2.com/v1"
)

with open("audio.wav", "rb") as f:
    audio_data = base64.b64encode(f.read()).decode()

completion = client.chat.completions.create(
    model="mimo-v2-omni",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What is being said in this audio?"},
                {
                    "type": "input_audio",
                    "input_audio": {
                        "data": audio_data,
                        "format": "wav"
                    }
                }
            ]
        }
    ]
)

print(completion.choices[0].message.content)