update: 恢复唤醒播放机制，待优化和改造（目前只有linkerai拥有正常保存唤醒音频to_tts）

main/xiaozhi-server/core/handle/receiveAudioHandle.py

@@ -1,11 +1,11 @@
 import time
 import json
-from core.handle.sendAudioHandle import send_stt_message
+import asyncio
+from core.utils.util import audio_to_data_stream
+from core.handle.abortHandle import handleAbortMessage
 from core.handle.intentHandler import handle_user_intent
 from core.utils.output_counter import check_device_output_limit
-from core.handle.abortHandle import handleAbortMessage
-from core.handle.sendAudioHandle import SentenceType
-from core.utils.util import audio_to_data_stream
+from core.handle.sendAudioHandle import send_stt_message, SentenceType
 
 TAG = __name__
 
@@ -13,7 +13,14 @@ TAG = __name__
 async def handleAudioMessage(conn, audio):
     # 当前片段是否有人说话
     have_voice = conn.vad.is_vad(conn, audio)
-
+    # 如果设备刚刚被唤醒，短暂忽略VAD检测
+    if have_voice and hasattr(conn, "just_woken_up") and conn.just_woken_up:
+        have_voice = False
+        # 设置一个短暂延迟后恢复VAD检测
+        conn.asr_audio.clear()
+        if not hasattr(conn, "vad_resume_task") or conn.vad_resume_task.done():
+            conn.vad_resume_task = asyncio.create_task(resume_vad_detection(conn))
+        return
     if have_voice:
         if conn.client_is_speaking:
             await handleAbortMessage(conn)
@@ -22,6 +29,13 @@ async def handleAudioMessage(conn, audio):
     # 接收音频
     await conn.asr.receive_audio(conn, audio, have_voice)
 
+
+async def resume_vad_detection(conn):
+    # 等待2秒后恢复VAD检测
+    await asyncio.sleep(1)
+    conn.just_woken_up = False
+
+
 async def startToChat(conn, text):
     # 检查输入是否是JSON格式（包含说话人信息）
     speaker_name = None
@@ -146,7 +160,6 @@ async def check_bind_device(conn):
         play_audio_frames(conn, music_path)
         conn.tts.tts_audio_queue.put((SentenceType.LAST, [], None))
 
-
 def play_audio_frames(conn, file_path):
     """播放音频文件并处理发送帧数据"""
     def handle_audio_frame(frame_data):