MiMo-V2.5-TTS-VoiceClone

import os
import base64
import urllib.request
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/v1",
)

# Example audio URL
audio_url = "https://example-files.cnbj1.mi-fds.com/example-files/audio/audio_example.wav"
audio_file = "audio_example.wav"

# Download the audio file from URL (skip if already exists)
if not os.path.exists(audio_file):
    urllib.request.urlretrieve(audio_url, audio_file)

# To use a local file directly, replace the above with:
# audio_file = "your_local_audio.wav"
with open(audio_file, "rb") as f:
    audio_bytes = f.read()
voice_base64 = base64.b64encode(audio_bytes).decode("utf-8")

completion = client.chat.completions.create(
    model="mimo-v2.5-tts-voiceclone",
    messages=[
        {
            "role": "user",
            "content": ""
        },
        {
            "role": "assistant",
            "content": "Yes, I had a sandwich."
        }
    ],
    audio={
        "format": "wav",
        "voice": f"data:audio/wav;base64,{voice_base64}"
    }
)

message = completion.choices[0].message
audio_bytes = base64.b64decode(message.audio.data)
with open("audio_file.wav", "wb") as f:
    f.write(audio_bytes)