Alibaba Cloud Model Studio:Qwen-Audio リアルタイム音声モデル

# pip install websockets pyaudio
import json
import os
import base64
import threading
import time
import pyaudio
import websocket

API_KEY = os.getenv("DASHSCOPE_API_KEY")
# 以下は China (Beijing) リージョンの WebSocket URL です。{WorkspaceId} (中括弧を含む) を実際のワークスペース ID に置き換えてください。URL はリージョンによって異なります。
API_URL = "wss://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api-ws/v1/realtime?model=qwen-audio-3.0-realtime-plus"

pya = pyaudio.PyAudio()
out_stream = pya.open(format=pyaudio.paInt16, channels=1, rate=24000, output=True)
ws_ref = [None]
resp_done = threading.Event()

def on_open(ws):
    ws_ref[0] = ws
    # プッシュツートークモードを設定 (turn_detection を null に設定)
    ws.send(json.dumps({
        "type": "session.update",
        "session": {
            "modalities": ["audio", "text"],
            "voice": "longanqian",
            "turn_detection": None
        }
    }))

def on_message(ws, message):
    event = json.loads(message)
    event_type = event["type"]
    if event_type == "response.audio.delta":
        out_stream.write(base64.b64decode(event["delta"]))
    elif event_type == "conversation.item.input_audio_transcription.completed":
        print(f"[ユーザー] {event['transcript']}")
    elif event_type == "response.audio_transcript.done":
        print(f"[LLM] {event['transcript']}")
    elif event_type == "response.done":
        resp_done.set()
    elif event_type == "error":
        print(f"[エラー] {event['error']['message']}")

def on_error(ws, error):
    print(f"エラー: {error}")

def record_and_send(ws):
    mic = pya.open(format=pyaudio.paInt16, channels=1, rate=16000, input=True)
    stop = threading.Event()

    def reader():
        while not stop.is_set():
            try:
                data = mic.read(3200, exception_on_overflow=False)
                ws.send(json.dumps({
                    "type": "input_audio_buffer.append",
                    "audio": base64.b64encode(data).decode()
                }))
            except Exception:
                break

    t = threading.Thread(target=reader, daemon=True)
    t.start()
    input()
    stop.set()
    t.join(timeout=1.0)
    mic.close()

headers = ["Authorization: Bearer " + API_KEY]
ws = websocket.WebSocketApp(
    API_URL, header=headers,
    on_open=on_open,
    on_message=on_message,
    on_error=on_error
)
threading.Thread(target=ws.run_forever, daemon=True).start()
time.sleep(2)

try:
    turn = 1
    while True:
        print(f"\n--- ターン {turn} ---")
        cmd = input("Enter キーを押して録音を開始します (終了するには q を入力)...")
        if cmd.strip().lower() in ["q", "quit"]:
            break
        print("録音中... 停止するには再度 Enter キーを押してください。")
        record_and_send(ws_ref[0])
        resp_done.clear()
        # オーディオをコミットして推論をトリガーします
        ws_ref[0].send(json.dumps({"type": "input_audio_buffer.commit"}))
        ws_ref[0].send(json.dumps({
            "type": "response.create",
            "response": {"modalities": ["audio", "text"]}
        }))
        print("モデルのレスポンスを待機中...")
        resp_done.wait(timeout=30)
        turn += 1
except KeyboardInterrupt:
    pass
finally:
    ws.close()
    out_stream.close()
    pya.terminate()
    print("\n会話が終了しました")

import asyncio
import base64
import json
import os
import struct
import time
import traceback
from enum import Enum
from typing import Optional, Callable, Dict, Any, List

import pyaudio
import websockets

from B64PCMPlayer import B64PCMPlayer

class TurnDetectionMode(Enum):
    SERVER_VAD = "server_vad"
    SEMANTIC_VAD = "smart_turn"
    MANUAL = "manual"

# ============ ツール関数の定義 ============

def get_weather(city: str) -> str:
    """都市の天気を照会します (本番環境では実際の API に置き換えてください)。"""
    return json.dumps({"temperature": 18, "condition": "sunny", "wind": "light breeze"})

def get_train_price(src: str, dst: str) -> str:
    """列車のチケット価格を照会します (本番環境では実際の API に置き換えてください)。"""
    return json.dumps({"price": 350, "seat": "second class", "note": "subject to 12306"})

# ============ ツールスキーマ ============

tools: List[Dict[str, Any]] = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "指定された都市の天気情報を照会します。",
            "parameters": {
                "type": "object",
                "properties": {
                    "city": {"type": "string", "description": "北京や上海などの都市名"}
                },
                "required": ["city"]
            }
        }
    },
    {
        "type": "function",
        "function": {
            "name": "get_train_price",
            "description": "2 つの都市間の列車のチケット価格を照会します。",
            "parameters": {
                "type": "object",
                "properties": {
                    "src": {"type": "string", "description": "出発都市"},
                    "dst": {"type": "string", "description": "到着都市"}
                },
                "required": ["src", "dst"]
            }
        }
    }
]

# 関数名から呼び出し可能オブジェクトへのマッピング
functions: Dict[str, Callable] = {
    "get_weather": get_weather,
    "get_train_price": get_train_price,
}

class FunRealtimeClient:

    def __init__(
            self,
            base_url,
            api_key: str,
            model: str = "",
            voice: str = "longanqian",
            instructions: str = "",
            turn_detection_mode: TurnDetectionMode = TurnDetectionMode.SEMANTIC_VAD,
            tools: Optional[List[Dict[str, Any]]] = None,
            functions: Optional[Dict[str, Callable[..., Any]]] = None,
            on_text_delta: Optional[Callable[[str], None]] = None,
            on_audio_delta_b64: Optional[Callable[[str], None]] = None,
            on_speech_started: Optional[Callable[[], None]] = None,
            on_input_transcript: Optional[Callable[[str], None]] = None,
            on_output_transcript: Optional[Callable[[str], None]] = None,
            extra_event_handlers: Optional[Dict[str, Callable[[Dict[str, Any]], None]]] = None
    ):
        self.base_url = base_url
        self.api_key = api_key
        self.model = model
        self.voice = voice
        self.instructions = instructions
        self.ws = None
        self.on_text_delta = on_text_delta
        # コールバックパラメータは base64 エンコードされた PCM オーディオです
        self.on_audio_delta_b64 = on_audio_delta_b64
        self.on_speech_started = on_speech_started
        self.on_input_transcript = on_input_transcript
        self.on_output_transcript = on_output_transcript
        self.turn_detection_mode = turn_detection_mode
        self.extra_event_handlers = extra_event_handlers or {}

        # 関数呼び出しの設定
        self.tools = tools or []
        self.functions = functions or {}

        # レスポンス状態の追跡 (割り込み処理とエコー抑制用)
        self._current_response_id = None
        self._current_item_id = None
        self._is_responding = False
        self._audio_suppressed = False
        self._print_input_transcript = True
        self._output_transcript_buffer = ""

    async def connect(self) -> None:
        """WebSocket 接続を確立し、セッション設定を送信します。"""
        url = f"{self.base_url}?model={self.model}"
        headers = {
            "Authorization": f"Bearer {self.api_key}",
            "x-dashscope-dataInspection": "disable",
        }
        self.ws = await websockets.connect(url, additional_headers=headers)

        session_config = {
            "modalities": ["text", "audio"],
            "voice": self.voice,
            "instructions": self.instructions,
            "input_audio_format": "pcm",
            "output_audio_format": "pcm",
            "turn_detection": {},
            "tools": self.tools
        }

        if self.turn_detection_mode == TurnDetectionMode.MANUAL:
            session_config['turn_detection'] = None
            await self.update_session(session_config)
        elif self.turn_detection_mode == TurnDetectionMode.SERVER_VAD:
            session_config['turn_detection'] = {
                "type": "server_vad",
                "threshold": 0.1,
                "silence_duration_ms": 900
            }
            await self.update_session(session_config)
        elif self.turn_detection_mode == TurnDetectionMode.SEMANTIC_VAD:
            session_config['turn_detection'] = {
                "type": "smart_turn"
            }
            await self.update_session(session_config)
        else:
            raise ValueError(f"Invalid turn detection mode: {self.turn_detection_mode}")

    async def send_event(self, event) -> None:
        event['event_id'] = "event_" + str(int(time.time() * 1000))
        await self.ws.send(json.dumps(event))

    async def update_session(self, config: Dict[str, Any]) -> None:
        """セッション設定を更新します。"""
        event = {
            "type": "session.update",
            "session": config
        }
        await self.send_event(event)

    async def stream_audio(self, audio_chunk: bytes) -> None:
        """RAW オーディオデータを API にストリーミングします。"""
        # 16 ビット 16 kHz モノラル PCM のみがサポートされています
        audio_b64 = base64.b64encode(audio_chunk).decode()
        await self.send_event({
            "type": "input_audio_buffer.append",
            "audio": audio_b64
        })

    async def commit_audio_buffer(self) -> None:
        """オーディオバッファをコミットして処理をトリガーします。"""
        await self.send_event({"type": "input_audio_buffer.commit"})

    async def create_response(self) -> None:
        """API にレスポンスの生成をリクエストします (手動モードまたは関数呼び出しの結果を返した後に呼び出します)。"""
        await self.send_event({"type": "response.create"})

    async def cancel_response(self) -> None:
        """現在のレスポンスをキャンセルします。"""
        await self.send_event({"type": "response.cancel"})

    async def handle_interruption(self):
        """現在のレスポンスに対するユーザーの割り込みを処理します。"""
        if not self._is_responding:
            return
        self._audio_suppressed = True
        if self._current_response_id:
            await self.cancel_response()
        self._is_responding = False
        self._current_response_id = None
        self._current_item_id = None

    @staticmethod
    def _format_event_for_log(event: Dict[str, Any]) -> str:
        """イベントをログ記録用に JSON としてフォーマットします。プライバシー保護のため、オーディオデータを省略します。"""
        event_type = event.get("type")
        if event_type == "response.audio.delta":
            delta = event.get("delta", "")
            redacted = dict(event)
            redacted["delta"] = f"<audio b64 omitted, length={len(delta)}>"
            return json.dumps(redacted, ensure_ascii=False)
        return json.dumps(event, ensure_ascii=False)

    async def _handle_function_call(self, event: Dict[str, Any]) -> None:
        """関数呼び出しを処理します：引数を解析し、関数を実行し、結果を返し、フォローアップの推論をトリガーします。"""
        call_id = event.get("call_id")
        name = event.get("name")
        arguments_str = event.get("arguments", "{}")

        print(f"[FunctionCall] Calling: {name}, call_id: {call_id}, args: {arguments_str}")

        try:
            arguments = json.loads(arguments_str) if arguments_str else {}
        except json.JSONDecodeError:
            arguments = {}

        func = self.functions.get(name)
        if func is None:
            output = json.dumps({"error": f"Unregistered function: {name}"})
        else:
            try:
                if asyncio.iscoroutinefunction(func):
                    result = await func(**arguments)
                else:
                    result = func(**arguments)
                output = str(result) if result is not None else ""
            except Exception as e:
                output = json.dumps({"error": str(e)})
                traceback.print_exc()

        # function_call_output を返します
        await self.send_event({
            "type": "conversation.item.create",
            "item": {
                "type": "function_call_output",
                "call_id": call_id,
                "output": output,
            }
        })

        # フォローアップの推論をトリガーします
        await self.create_response()

    async def handle_messages(self) -> None:
        try:
            async for message in self.ws:
                event = json.loads(message)
                event_type = event.get("type")

                print(self._format_event_for_log(event))

                if event_type == "error":
                    continue
                elif event_type == "response.created":
                    self._current_response_id = event.get("response", {}).get("id")
                    self._is_responding = True
                    self._audio_suppressed = False
                elif event_type == "response.output_item.added":
                    self._current_item_id = event.get("item", {}).get("id")
                elif event_type == "response.done":
                    self._is_responding = False
                    self._current_response_id = None
                    self._current_item_id = None
                elif event_type == "input_audio_buffer.speech_started":
                    print("----------------Speech Started----------------")
                    if self.on_speech_started:
                        self.on_speech_started()
                    if self._is_responding:
                        await self.handle_interruption()
                elif event_type == "response.audio.delta":
                    if self._audio_suppressed:
                        continue
                    if self.on_audio_delta_b64:
                        self.on_audio_delta_b64(event["delta"])
                elif event_type == "response.function_call_arguments.done":
                    await self._handle_function_call(event)
                elif event_type in self.extra_event_handlers:
                    self.extra_event_handlers[event_type](event)
                elif event_type == "input_audio_buffer.speech_stopped":
                    print("----------------Speech Stopped----------------")
        except websockets.exceptions.ConnectionClosed:
            print(" Connection closed")
        except Exception as e:
            print(" Error in message handling: ", str(e))
            traceback.print_exc()

    async def close(self) -> None:
        """WebSocket 接続を閉じます。"""
        if self.ws:
            await self.ws.close()

def _audio_energy(audio_data: bytes) -> float:
    count = len(audio_data) // 2
    if count == 0:
        return 0.0
    samples = struct.unpack(f'<{count}h', audio_data)
    return sum(abs(s) for s in samples) / count

async def record_and_send(client, player, echo_suppression=True):
    p = pyaudio.PyAudio()
    stream = p.open(format=pyaudio.paInt16, channels=1, rate=16000, input=True)
    print("Recording started. Speak into the microphone...")
    if echo_suppression:
        print("Note: Echo suppression is enabled (microphone is muted while AI is speaking, interruption not supported). If you are using headphones, set echo_suppression=False to enable interruption.")
    else:
        print("Note: Headphone mode. Voice interruption is supported.")
    playback_end_time = 0.0
    NOISE_GATE_THRESHOLD = 500
    try:
        while True:
            audio_data = await asyncio.to_thread(stream.read, 3200, False)
            if echo_suppression:
                is_active = client._is_responding or player.is_playing()
                if is_active:
                    playback_end_time = time.time()
                    await asyncio.sleep(0.02)
                    continue
                if time.time() - playback_end_time < 0.5:
                    await asyncio.sleep(0.02)
                    continue
            else:
                if client._is_responding or player.is_playing():
                    if _audio_energy(audio_data) < NOISE_GATE_THRESHOLD:
                        await asyncio.sleep(0.02)
                        continue
            await client.stream_audio(audio_data)
            await asyncio.sleep(0.02)
    finally:
        stream.stop_stream(); stream.close(); p.terminate()

async def main():
    pya = pyaudio.PyAudio()
    # 出力サンプリングレートは 24 kHz で、サーバー側のオーディオ形式と一致します
    player = B64PCMPlayer(pya, sample_rate=24000)

    client = FunRealtimeClient(
        # 以下は China (Beijing) リージョンの WebSocket URL です。{WorkspaceId} (中括弧を含む) を実際のワークスペース ID に置き換えてください。URL はリージョンによって異なります。
        base_url="wss://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api-ws/v1/realtime",
        api_key=os.environ['DASHSCOPE_API_KEY'],
        model="qwen-audio-3.0-realtime-plus",
        voice="longanqian",
        turn_detection_mode=TurnDetectionMode.SERVER_VAD,
        tools=tools,
        functions=functions,
        on_audio_delta_b64=player.add_data,
        # 音声割り込み時に再生バッファをクリアします
        on_speech_started=player.cancel_playing,
    )

    await client.connect()
    print("Connected. Starting real-time conversation (Function Calling enabled)...")

    try:
        await asyncio.gather(client.handle_messages(), record_and_send(client, player, echo_suppression=False))
    finally:
        await client.close()
        player.shutdown()
        pya.terminate()

if __name__ == "__main__":
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nProgram exited.")