'commit'

TTS/testTtsModel.py

@@ -0,0 +1,57 @@
+# coding=utf-8
+# Installation instructions for pyaudio:
+# CentOS
+#   sudo yum install -y portaudio portaudio-devel && pip install pyaudio
+# Microsoft Windows
+#   python -m pip install pyaudio
+
+import os
+import sys
+
+# 添加项目根目录到 sys.path 以便导入 Util
+root_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+if root_dir not in sys.path:
+    sys.path.append(root_dir)
+
+from Util.AlyTtsKit import QwenTTSManager
+
+# ======= 测试配置 =======
+VOICE_FILE_PATH = os.path.join(os.path.dirname(__file__), "voice.mp3")
+
+def main():
+    """
+    测试函数
+    """
+    print('[系统] 启动 Qwen TTS 测试 (使用 AlyTtsKit)...')
+    
+    # 待合成的文本
+    test_texts = [
+        '您好，我是您的 AI 助手。',
+        '现在正在测试抽取到 Util 目录下的 AlyTtsKit 功能。',
+        '希望这次重构能让代码更加模块化！'
+    ]
+
+    try:
+        # 1. 初始化管理器
+        tts_manager = QwenTTSManager()
+
+        # 2. 创建/获取音色
+        if not os.path.exists(VOICE_FILE_PATH):
+            print(f'[错误] 测试音频文件不存在: {VOICE_FILE_PATH}')
+            return
+
+        print('[系统] 正在进行声音复刻...')
+        voice_id = tts_manager.create_voice_enrollment(VOICE_FILE_PATH)
+        print(f'[系统] 声音复刻成功，Voice ID: {voice_id}')
+
+        # 3. 执行合成并播放
+        print('[系统] 开始语音合成...')
+        tts_manager.start_synthesis(voice_id, test_texts)
+        
+        print('[系统] 测试完成。')
+
+    except Exception as e:
+        print(f'[系统] 发生错误: {e}')
+
+if __name__ == '__main__':
+    main()

Util/AlyTtsKit.py

@@ -0,0 +1,136 @@
+# coding=utf-8
+import pyaudio
+import os
+import sys
+import requests
+import base64
+import pathlib
+import threading
+import time
+import dashscope
+from dashscope.audio.qwen_tts_realtime import QwenTtsRealtime, QwenTtsRealtimeCallback, AudioFormat
+
+# 添加项目根目录到 sys.path 以便导入 Config
+root_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+if root_dir not in sys.path:
+    sys.path.append(root_dir)
+
+try:
+    from Config.Config import ALY_LLM_API_KEY
+except ImportError:
+    ALY_LLM_API_KEY = os.getenv("DASHSCOPE_API_KEY")
+
+# ======= 常量配置 =======
+DEFAULT_TARGET_MODEL = "qwen3-tts-vc-realtime-2026-01-15"
+DEFAULT_PREFERRED_NAME = "guanyu"
+DEFAULT_AUDIO_MIME_TYPE = "audio/mpeg"
+
+class MyCallback(QwenTtsRealtimeCallback):
+    """
+    自定义 TTS 流式回调
+    """
+    def __init__(self):
+        self.complete_event = threading.Event()
+        self._player = pyaudio.PyAudio()
+        self._stream = self._player.open(
+            format=pyaudio.paInt16, channels=1, rate=24000, output=True
+        )
+
+    def on_open(self) -> None:
+        print('[TTS] 连接已建立')
+
+    def on_close(self, close_status_code, close_msg) -> None:
+        if self._stream:
+            self._stream.stop_stream()
+            self._stream.close()
+        if self._player:
+            self._player.terminate()
+        print(f'[TTS] 连接关闭 code={close_status_code}, msg={close_msg}')
+
+    def on_event(self, response: dict) -> None:
+        try:
+            event_type = response.get('type', '')
+            if event_type == 'session.created':
+                print(f'[TTS] 会话开始: {response["session"]["id"]}')
+            elif event_type == 'response.audio.delta':
+                audio_data = base64.b64decode(response['delta'])
+                self._stream.write(audio_data)
+            elif event_type == 'response.done':
+                print(f'[TTS] 响应完成')
+            elif event_type == 'session.finished':
+                print('[TTS] 会话结束')
+                self.complete_event.set()
+        except Exception as e:
+            print(f'[Error] 处理回调事件异常: {e}')
+
+    def wait_for_finished(self):
+        self.complete_event.wait()
+
+class QwenTTSManager:
+    """
+    通义千问实时语音合成管理类
+    """
+    def __init__(self, api_key=ALY_LLM_API_KEY, model=DEFAULT_TARGET_MODEL):
+        self.api_key = api_key
+        self.model = model
+        dashscope.api_key = self.api_key
+        self.callback = None
+        self.qwen_tts_realtime = None
+
+    def create_voice_enrollment(self, file_path, preferred_name=DEFAULT_PREFERRED_NAME):
+        """
+        创建声音复刻音色
+        """
+        file_path_obj = pathlib.Path(file_path)
+        if not file_path_obj.exists():
+            raise FileNotFoundError(f"音频文件不存在: {file_path}")
+
+        base64_str = base64.b64encode(file_path_obj.read_bytes()).decode()
+        data_uri = f"data:{DEFAULT_AUDIO_MIME_TYPE};base64,{base64_str}"
+
+        url = "https://dashscope.aliyuncs.com/api/v1/services/audio/tts/customization"
+        payload = {
+            "model": "qwen-voice-enrollment",
+            "input": {
+                "action": "create",
+                "target_model": self.model,
+                "preferred_name": preferred_name,
+                "audio": {"data": data_uri}
+            }
+        }
+        headers = {
+            "Authorization": f"Bearer {self.api_key}",
+            "Content-Type": "application/json"
+        }
+
+        resp = requests.post(url, json=payload, headers=headers)
+        if resp.status_code != 200:
+            raise RuntimeError(f"创建 voice 失败: {resp.status_code}, {resp.text}")
+
+        return resp.json()["output"]["voice"]
+
+    def start_synthesis(self, voice_id, text_list):
+        """
+        开始实时语音合成并播放
+        """
+        self.callback = MyCallback()
+        self.qwen_tts_realtime = QwenTtsRealtime(
+            model=self.model,
+            callback=self.callback,
+            url='wss://dashscope.aliyuncs.com/api-ws/v1/realtime'
+        )
+        self.qwen_tts_realtime.connect()
+        
+        self.qwen_tts_realtime.update_session(
+            voice=voice_id,
+            response_format=AudioFormat.PCM_24000HZ_MONO_16BIT,
+            mode='server_commit'
+        )
+
+        for text in text_list:
+            print(f'[发送文本]: {text}')
+            self.qwen_tts_realtime.append_text(text)
+            time.sleep(0.1)
+
+        self.qwen_tts_realtime.finish()
+        self.callback.wait_for_finished()