update:优化唤醒词答复

update:优化唤醒词答复

main/xiaozhi-server/config.yaml

@@ -57,6 +57,12 @@ delete_audio: true
 close_connection_no_voice_time: 120
 # TTS请求超时时间(秒)
 tts_timeout: 10
+# 开场是否回复唤醒词
+enable_greeting: true
+# 说完话是否开启提示音
+enable_stop_tts_notify: false
+# 说完话是否开启提示音，音效地址
+stop_tts_notify_voice: "config/assets/tts_notify.mp3"
 
 CMD_exit:
   - "退出"
@@ -514,3 +520,16 @@ module_test:
     - "你好，请介绍一下你自己"
     - "What's the weather like today?"
     - "请用100字概括量子计算的基本原理和应用前景"
+
+# 唤醒词，用于识别唤醒词还是讲话内容
+wakeup_words:
+  - "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"

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

@@ -7,12 +7,26 @@ from core.utils.util import remove_punctuation_and_length, get_string_no_punctua
 TAG = __name__
 logger = setup_logging()
 
+
 async def sendAudioMessage(conn, audios, text, text_index=0):
     # 发送句子开始消息
     if text_index == conn.tts_first_text_index:
         logger.bind(tag=TAG).info(f"发送第一段语音: {text}")
     await send_tts_message(conn, "sentence_start", text)
 
+    # 播放音频
+    await sendAudio(conn, audios)
+
+    await send_tts_message(conn, "sentence_end", text)
+
+    # 发送结束消息（如果是最后一个文本）
+    if conn.llm_finish_task and text_index == conn.tts_last_text_index:
+        await send_tts_message(conn, 'stop', None)
+        if conn.close_after_chat:
+            await conn.close()
+
+# 播放音频
+async def sendAudio(conn, audios):
     # 流控参数优化
     original_frame_duration = 60  # 原始帧时长（毫秒）
     adjusted_frame_duration = int(original_frame_duration * 0.8)  # 缩短20%
@@ -42,13 +56,6 @@ async def sendAudioMessage(conn, audios, text, text_index=0):
     if compensation > 0:
         await asyncio.sleep(compensation)
 
-    await send_tts_message(conn, "sentence_end", text)
-
-    # 发送结束消息（如果是最后一个文本）
-    if conn.llm_finish_task and text_index == conn.tts_last_text_index:
-        await send_tts_message(conn, 'stop', None)
-        if conn.close_after_chat:
-            await conn.close()
 
 async def send_tts_message(conn, state, text=None):
     """发送 TTS 状态消息"""
@@ -60,10 +67,20 @@ async def send_tts_message(conn, state, text=None):
     if text is not None:
         message["text"] = text
 
-    await conn.websocket.send(json.dumps(message))
+    # TTS播放结束
     if state == "stop":
+        # 播放提示音
+        tts_notify = conn.config.get("enable_stop_tts_notify", False)
+        if tts_notify:
+            stop_tts_notify_voice = conn.config.get("stop_tts_notify_voice", "config/assets/tts_notify.mp3")
+            audios, duration = conn.tts.audio_to_opus_data(stop_tts_notify_voice)
+            await sendAudio(conn, audios)
+        # 清除服务端讲话状态
         conn.clearSpeakStatus()
 
+    # 发送消息到客户端
+    await conn.websocket.send(json.dumps(message))
+
 
 async def send_stt_message(conn, text):
     """发送 STT 状态消息"""

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

@@ -2,7 +2,9 @@ from config.logger import setup_logging
 import json
 from core.handle.abortHandle import handleAbortMessage
 from core.handle.helloHandle import handleHelloMessage
+from core.utils.util import remove_punctuation_and_length
 from core.handle.receiveAudioHandle import startToChat, handleAudioMessage
+from core.handle.sendAudioHandle import send_stt_message, send_tts_message
 from core.handle.iotHandle import handleIotDescriptors, handleIotStatus
 
 TAG = __name__
@@ -38,7 +40,21 @@ async def handleTextMessage(conn, message):
                 conn.client_have_voice = False
                 conn.asr_audio.clear()
                 if "text" in msg_json:
-                    await startToChat(conn, msg_json["text"])
+                    text = msg_json["text"]
+                    _, text = remove_punctuation_and_length(text)
+
+                    # 识别是否是唤醒词
+                    is_wakeup_words = text in conn.config.get("wakeup_words")
+                    # 是否开启唤醒词回复
+                    enable_greeting = conn.config.get("enable_greeting", True)
+
+                    if is_wakeup_words and not enable_greeting:
+                        # 如果是唤醒词，且关闭了唤醒词回复，就不用回答
+                        await send_stt_message(conn, text)
+                        await send_tts_message(conn, "stop", None)
+                    else:
+                        # 否则需要LLM对文字内容进行答复
+                        await startToChat(conn, text)
         elif msg_json["type"] == "iot":
             if "descriptors" in msg_json:
                 await handleIotDescriptors(conn, msg_json["descriptors"])