update:流式优化暂不稳定，先回滚到早期代码

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

@@ -1,21 +1,28 @@
-import time
-import json
-from core.handle.abortHandle import handleAbortMessage
+from core.handle.sendAudioHandle import send_stt_message
 from core.handle.intentHandler import handle_user_intent
 from core.utils.output_counter import check_device_output_limit
-from core.utils.util import play_audio_frames, play_audio_response
-from core.handle.sendAudioHandle import send_stt_message, SentenceType
+from core.handle.abortHandle import handleAbortMessage
+import time
+import asyncio
+import json
+from core.handle.sendAudioHandle import SentenceType
+from core.utils.util import audio_to_data
 
 TAG = __name__
 
 
 async def handleAudioMessage(conn, audio):
-    # 检查是否在唤醒处理锁定期内
-    if getattr(conn, 'wakeup_processing_lock', 0) > time.monotonic():
-        return
-    
     # 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)
@@ -24,11 +31,18 @@ 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
     actual_text = text
-
+    
     try:
         # 尝试解析JSON格式的输入
         if text.strip().startswith('{') and text.strip().endswith('}'):
@@ -37,13 +51,13 @@ async def startToChat(conn, text):
                 speaker_name = data['speaker']
                 actual_text = data['content']
                 conn.logger.bind(tag=TAG).info(f"解析到说话人信息: {speaker_name}")
-
+                
                 # 直接使用JSON格式的文本，不解析
                 actual_text = text
     except (json.JSONDecodeError, KeyError):
         # 如果解析失败，继续使用原始文本
         pass
-
+    
     # 保存说话人信息到连接对象
     if speaker_name:
         conn.current_speaker = speaker_name
@@ -107,7 +121,8 @@ async def max_out_size(conn):
     text = "不好意思，我现在有点事情要忙，明天这个时候我们再聊，约好了哦！明天不见不散，拜拜！"
     await send_stt_message(conn, text)
     file_path = "config/assets/max_output_size.wav"
-    play_audio_response(conn, {"text": text, "file_path": file_path})
+    opus_packets, _ = audio_to_data(file_path)
+    conn.tts.tts_audio_queue.put((SentenceType.LAST, opus_packets, text))
     conn.close_after_chat = True
 
 
@@ -125,15 +140,16 @@ async def check_bind_device(conn):
 
         # 播放提示音
         music_path = "config/assets/bind_code.wav"
-        conn.tts.tts_audio_queue.put((SentenceType.FIRST, [], text))
-        play_audio_frames(conn, music_path)
+        opus_packets, _ = audio_to_data(music_path)
+        conn.tts.tts_audio_queue.put((SentenceType.FIRST, opus_packets, text))
 
         # 逐个播放数字
         for i in range(6):  # 确保只播放6位数字
             try:
                 digit = conn.bind_code[i]
                 num_path = f"config/assets/bind_code/{digit}.wav"
-                play_audio_frames(conn, num_path)
+                num_packets, _ = audio_to_data(num_path)
+                conn.tts.tts_audio_queue.put((SentenceType.MIDDLE, num_packets, None))
             except Exception as e:
                 conn.logger.bind(tag=TAG).error(f"播放数字音频失败: {e}")
                 continue
@@ -142,4 +158,5 @@ async def check_bind_device(conn):
         text = f"没有找到该设备的版本信息，请正确配置 OTA地址，然后重新编译固件。"
         await send_stt_message(conn, text)
         music_path = "config/assets/bind_not_found.wav"
-        play_audio_response(conn, {"text": text, "file_path": music_path})
+        opus_packets, _ = audio_to_data(music_path)
+        conn.tts.tts_audio_queue.put((SentenceType.LAST, opus_packets, text))