音声クローニング

# Requirements: dashscope >= 1.26.5, pyaudio
import os
import requests
import base64
import pathlib
import time
import pyaudio
from dashscope.audio.qwen_omni import MultiModality, OmniRealtimeCallback, OmniRealtimeConversation
import dashscope
# 中国（北京）リージョン。サンプルにワークスペース ID を入力してください。URL はリージョンによって異なります。
dashscope.base_http_api_url = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1"

# ======= Configuration =======
DEFAULT_TARGET_MODEL = "qwen3.8-omni-flash-realtime"  # Must be the same model for cloning and conversation
DEFAULT_PREFERRED_NAME = "guanyu"
DEFAULT_AUDIO_MIME_TYPE = "audio/mpeg"
VOICE_FILE_PATH = "voice.mp3"  # Path to the local audio file for voice cloning

def create_voice(file_path: str,
                 target_model: str = DEFAULT_TARGET_MODEL,
                 preferred_name: str = DEFAULT_PREFERRED_NAME,
                 audio_mime_type: str = DEFAULT_AUDIO_MIME_TYPE) -> str:
    """
    Create a custom voice and return the voice parameter.
    """
    # API keys differ between the Singapore and Beijing regions. Get an API key: https://www.alibabacloud.com/help/model-studio/get-api-key
    # If you haven't set an environment variable, replace the following line with: api_key = "sk-xxx"
    api_key = os.getenv("DASHSCOPE_API_KEY")

    file_path_obj = pathlib.Path(file_path)
    if not file_path_obj.exists():
        raise FileNotFoundError(f"Audio file not found: {file_path}")

    base64_str = base64.b64encode(file_path_obj.read_bytes()).decode()
    data_uri = f"data:{audio_mime_type};base64,{base64_str}"

    # シンガポールリージョンの URL です。サンプルにワークスペース ID を入力してください。URL はリージョンによって異なります。
    url = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/audio/tts/customization"
    payload = {
        "model": "qwen-voice-enrollment",
        "parameters": {"voice_clone_mode": "normal"},
        "input": {
            "action": "create",
            "target_model": target_model,
            "preferred_name": preferred_name,
            "audio": {"data": data_uri}
        }
    }
    headers = {
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json"
    }

    resp = requests.post(url, json=payload, headers=headers)
    if resp.status_code != 200:
        raise RuntimeError(f"Failed to create voice: {resp.status_code}, {resp.text}")

    try:
        return resp.json()["output"]["voice"]
    except (KeyError, ValueError) as e:
        raise RuntimeError(f"Failed to parse voice response: {e}")

class SimpleCallback(OmniRealtimeCallback):
    def __init__(self, pya):
        self.pya = pya
        self.out = None
    def on_open(self):
        self.out = self.pya.open(
            format=pyaudio.paInt16,
            channels=1,
            rate=24000,
            output=True
        )
    def on_event(self, response):
        if response['type'] == 'response.audio.delta':
            self.out.write(base64.b64decode(response['delta']))
        elif response['type'] == 'conversation.item.input_audio_transcription.completed':
            print(f"[User] {response['transcript']}")
        elif response['type'] == 'response.audio_transcript.done':
            print(f"[LLM] {response['transcript']}")

if __name__ == '__main__':
    # If you haven't set an environment variable, replace the following line with: dashscope.api_key = "sk-xxx"
    dashscope.api_key = os.getenv("DASHSCOPE_API_KEY")
    # シンガポールリージョンの URL です。サンプルにワークスペース ID を入力してください。URL はリージョンによって異なります。
    url = "wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/realtime"

    # Step 1: Clone a voice
    voice = create_voice(VOICE_FILE_PATH)
    print(f"Voice cloning complete. Voice: {voice}")

    # Step 2: Start a real-time conversation with the cloned voice
    pya = pyaudio.PyAudio()
    callback = SimpleCallback(pya)
    conv = OmniRealtimeConversation(model=DEFAULT_TARGET_MODEL, callback=callback, url=url)
    conv.connect()
    conv.update_session(
        output_modalities=[MultiModality.AUDIO, MultiModality.TEXT],
        voice=voice  # Use the cloned voice
    )
    mic = pya.open(format=pyaudio.paInt16, channels=1, rate=16000, input=True)
    print("Conversation started. Speak into your microphone (Ctrl+C to exit)...")
    try:
        while True:
            audio_data = mic.read(3200, exception_on_overflow=False)
            conv.append_audio(base64.b64encode(audio_data).decode())
            time.sleep(0.01)
    except KeyboardInterrupt:
        conv.close()
        mic.close()
        callback.out.close()
        pya.terminate()
        print("\nConversation ended")