update：双麦实时打断

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

@@ -92,7 +92,13 @@ async def wakeupWordsResponse(conn):
 
     """唤醒词响应"""
     wakeup_word = random.choice(WAKEUP_CONFIG["words"])
-    result = conn.llm.response_no_stream(conn.config["prompt"], wakeup_word)
+    question = (
+        "此刻用户正在和你说```"
+        + wakeup_word
+        + "```。\n请你根据以上用户的内容，进行简短回复，文字内容控制在15个字以内。\n"
+        + "请勿对这条内容本身进行任何解释和回应，仅返回对用户的内容的回复。"
+    )
+    result = conn.llm.response_no_stream(conn.config["prompt"], question)
     if result is None or result == "":
         return
     tts_file = await asyncio.to_thread(conn.tts.to_tts, result)

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

@@ -1,6 +1,7 @@
 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.handle.abortHandle import handleAbortMessage
 import time
 from core.handle.sendAudioHandle import SentenceType
 from core.utils.util import audio_to_data
@@ -12,11 +13,14 @@ async def handleAudioMessage(conn, audio):
     if conn.vad is None:
         conn.logger.bind(tag=TAG).warning("VAD模块未初始化，继续等待")
         return
-    if conn.asr is None:
-        conn.logger.bind(tag=TAG).warning("ASR模块未初始化，继续等待")
+    if conn.asr is None or not hasattr(conn.asr, "conn") or conn.asr.conn is None:
+        conn.logger.bind(tag=TAG).warning("ASR模块未初始化或通道未就绪，继续等待")
         return
     # 当前片段是否有人说话
     have_voice = conn.vad.is_vad(conn, audio)
+    if have_voice:
+        if conn.client_is_speaking:
+            await handleAbortMessage(conn)
     # 设备长时间空闲检测，用于say goodbye
     await no_voice_close_connect(conn, have_voice)
     # 接收音频
@@ -35,6 +39,8 @@ async def startToChat(conn, text):
         ):
             await max_out_size(conn)
             return
+    if conn.client_is_speaking:
+        await handleAbortMessage(conn)
 
     # 首先进行意图分析
     intent_handled = await handle_user_intent(conn, text)
@@ -72,7 +78,7 @@ async def no_voice_close_connect(conn, have_voice):
                 return
             prompt = end_prompt.get("prompt")
             if not prompt:
-                prompt = "请你以“时间过得真快”未来头，用富有感情、依依不舍的话来结束这场对话吧。！"
+                prompt = "请你以```时间过得真快```未来头，用富有感情、依依不舍的话来结束这场对话吧。！"
             await startToChat(conn, prompt)
 
 

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

@@ -62,6 +62,7 @@ async def sendAudioMessage(conn, sentenceType, audios, text):
     # 发送结束消息（如果是最后一个文本）
     if conn.llm_finish_task and sentenceType == SentenceType.LAST:
         await send_tts_message(conn, "stop", None)
+        conn.client_is_speaking = False
         if conn.close_after_chat:
             await conn.close()
 
@@ -88,6 +89,7 @@ async def sendAudio(conn, audios, pre_buffer=True):
     # 播放剩余音频帧
     for opus_packet in remaining_audios:
         if conn.client_abort:
+            conn.client_abort = False
             return
 
         # 每分钟重置一次计时器
@@ -141,4 +143,5 @@ async def send_stt_message(conn, text):
     await conn.websocket.send(
         json.dumps({"type": "stt", "text": stt_text, "session_id": conn.session_id})
     )
+    conn.client_is_speaking = True
     await send_tts_message(conn, "start")

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

@@ -58,6 +58,7 @@ async def handleTextMessage(conn, message):
                         # 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, original_text)
                         await send_tts_message(conn, "stop", None)
+                        conn.client_is_speaking = False
                     elif is_wakeup_words:
                         # 上报纯文字数据（复用ASR上报功能，但不提供音频数据）
                         enqueue_asr_report(conn, "嘿，你好呀", [])