Merge pull request #1500 from xinnan-tech/fix-stream-mem

Fix stream mem

main/manager-api/src/main/java/xiaozhi/common/constant/Constant.java

@@ -227,7 +227,7 @@ public interface Constant {
     /**
      * 版本号
      */
-    public static final String VERSION = "0.5.4";
+    public static final String VERSION = "0.5.5";
 
     /**
      * 无效固件URL

main/manager-api/src/main/resources/db/changelog/202506080955.sql

@@ -0,0 +1,3 @@
+-- 智控台开启唤醒词加速
+update `sys_params` set param_value = '你好小智;你好小志;小爱同学;你好小鑫;你好小新;小美同学;小龙小龙;喵喵同学;小滨小滨;小冰小冰;嘿你好呀' where param_code = 'wakeup_words';
+update `sys_params` set param_value = 'true' where param_code = 'enable_wakeup_words_response_cache';

main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml

@@ -198,3 +198,10 @@ databaseChangeLog:
         - sqlFile:
             encoding: utf8
             path: classpath:db/changelog/202506051538.sql
+  - changeSet:
+      id: 202506080955
+      author: hrz
+      changes:
+        - sqlFile:
+            encoding: utf8
+            path: classpath:db/changelog/202506080955.sql

main/xiaozhi-server/config/logger.py

@@ -5,7 +5,7 @@ from config.config_loader import load_config
 from config.settings import check_config_file
 from datetime import datetime
 
-SERVER_VERSION = "0.5.4"
+SERVER_VERSION = "0.5.5"
 _logger_initialized = False
 
 

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

@@ -3,7 +3,7 @@ import json
 import random
 import asyncio
 from core.utils.util import audio_to_data
-from core.handle.sendAudioHandle import send_stt_message
+from core.handle.sendAudioHandle import sendAudioMessage, send_stt_message
 from core.utils.util import remove_punctuation_and_length, opus_datas_to_wav_bytes
 from core.providers.tts.dto.dto import ContentType, SentenceType
 from core.handle.mcpHandle import (
@@ -74,8 +74,10 @@ async def checkWakeupWords(conn, text):
     # 播放唤醒词回复
     conn.client_abort = False
     opus_packets, _ = audio_to_data(response["file_path"])
-    conn.tts.tts_audio_queue.put((SentenceType.FIRST, opus_packets, response["text"]))
+
-    conn.tts.tts_audio_queue.put((SentenceType.LAST, [], None))
+    conn.logger.bind(tag=TAG).info(f"播放唤醒词回复: {response['text']}")
+    await sendAudioMessage(conn, SentenceType.FIRST, opus_packets, response["text"])
+    await sendAudioMessage(conn, SentenceType.LAST, [], None)
 
     # 检查是否需要更新唤醒词回复
     if time.time() - response["time"] > WAKEUP_CONFIG["refresh_time"]:

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

@@ -34,6 +34,7 @@ emoji_map = {
 
 async def sendAudioMessage(conn, sentenceType, audios, text):
     # 发送句子开始消息
+    conn.logger.bind(tag=TAG).info(f"发送音频消息: {sentenceType}, {text}")
     if text is not None:
         emotion = analyze_emotion(text)
         emoji = emoji_map.get(emotion, "🙂")  # 默认使用笑脸

main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py

@@ -188,10 +188,8 @@ class TTSProvider(TTSProviderBase):
 
     def tts_text_priority_thread(self):
         """火山引擎双流式TTS的文本处理线程"""
-        logger.bind(tag=TAG).info("TTS文本处理线程启动")
         while not self.conn.stop_event.is_set():
             try:
-                logger.bind(tag=TAG).debug("等待TTS文本队列消息...")
                 message = self.tts_text_queue.get(timeout=1)
                 logger.bind(tag=TAG).debug(
                     f"收到TTS任务｜{message.sentence_type.name} ｜ {message.content_type.name} | 会话ID: {self.conn.sentence_id}"

main/xiaozhi-server/core/providers/tts/linkerai.py

@@ -93,6 +93,8 @@ class TTSProvider(TTSProviderBase):
                 self.processed_chars += len(full_text)
             else:
                 self._process_before_stop_play_files()
+        else:
+            self._process_before_stop_play_files()
 
     def to_tts_single_stream(self, text, is_last=False):
         try:
@@ -171,6 +173,8 @@ class TTSProvider(TTSProviderBase):
                     self.pcm_buffer.clear()
                     opus_datas_cache = []
 
+                    self.tts_audio_queue.put((SentenceType.FIRST, [], text))
+
                     # 兼容 iter_chunked / iter_chunks / iter_any
                     async for chunk in resp.content.iter_any():
                         data = chunk[0] if isinstance(chunk, (list, tuple)) else chunk
@@ -191,7 +195,7 @@ class TTSProvider(TTSProviderBase):
                             if opus:
                                 if self.segment_count < 10:  # 前10个片段直接发送
                                     self.tts_audio_queue.put(
-                                        (SentenceType.MIDDLE, opus, text)
+                                        (SentenceType.MIDDLE, opus, None)
                                     )
                                     self.segment_count += 1
                                 else:
@@ -206,7 +210,7 @@ class TTSProvider(TTSProviderBase):
                             if self.segment_count < 10:  # 前10个片段直接发送
                                 # 直接发送
                                 self.tts_audio_queue.put(
-                                    (SentenceType.MIDDLE, opus, text)
+                                    (SentenceType.MIDDLE, opus, None)
                                 )
                                 self.segment_count += 1
                             else:
@@ -217,7 +221,7 @@ class TTSProvider(TTSProviderBase):
                     # 如果不是前10个片段，发送缓存的数据
                     if self.segment_count >= 10 and opus_datas_cache:
                         self.tts_audio_queue.put(
-                            (SentenceType.MIDDLE, opus_datas_cache, text)
+                            (SentenceType.MIDDLE, opus_datas_cache, None)
                         )
 
                     # 如果是最后一段，输出音频获取完毕