add:支持手动按住说话

README.md

@@ -27,16 +27,16 @@
 ## 已实现
 
 - `xiaozhi-esp32` 通信 WebSocket 协议
-- 支持实时打断对话，试一下在聊天的时候说一句`你好小智`
+- 支持唤醒对话、手动对话、实时打断对话
 - 支持国语、粤语、英语、日语、韩语 5 种语言识别（FunASR（默认））
 - 自由更换 LLM（支持ChatGLM（默认）、Dify、DeepSeek）
 - 自由更换 TTS（支持EdgeTTS（默认）、火山引擎豆包TTS）
 
 ## 正在实现
 
-- 按键手动对话
 - 长时间不聊天进入休眠状态
 - 对话记忆
+- 更换心情模式
 
 ## 本项目依赖服务
 

README_en.md

@@ -32,16 +32,16 @@ To fully experience this project, follow these steps:
 ## Implemented
 
 - `xiaozhi-esp32` WebSocket communication protocol
-- Support interrupt dialogue in real time, try to say a sentence when chatting `你好小智`
+- Supports wake-word initiated dialogue, manual dialogue, and real-time interruption of dialogue.
 - Support for 5 languages: Mandarin, Cantonese, English, Japanese, Korean (FunASR - default)
 - Flexible LLM switching (ChatGLM - default, Dify, DeepSeek)
 - Flexible TTS switching (EdgeTTS - default, ByteDance Doubao TTS)
 
 ## In Progress
 
-- Manual button-triggered dialogue
 - Sleep mode after inactivity
 - Dialogue memory
+- Change the mood mode
 
 ## Dependencies
 

core/connection.py

@@ -12,8 +12,6 @@ from collections import deque
 from core.utils.util import is_segment
 from core.utils.dialogue import Message, Dialogue
 from core.handle.textHandle import handleTextMessage
-from core.handle.abortHandle import handleAbortMessage
-from core.handle.helloHandle import handleHelloMessage
 from core.utils.util import get_string_no_punctuation_or_emoji
 from concurrent.futures import ThreadPoolExecutor, TimeoutError
 from core.handle.audioHandle import handleAudioMessage, sendAudioMessage
@@ -29,7 +27,10 @@ class ConnectionHandler:
         self.session_id = None
         self.prompt = None
         self.welcome_msg = None
+
+        # 客户端状态相关
         self.client_abort = False
+        self.client_listen_mode = "auto"
 
         # 线程任务相关
         self.loop = asyncio.get_event_loop()
@@ -91,22 +92,10 @@ class ConnectionHandler:
     async def _route_message(self, message):
         """消息路由"""
         if isinstance(message, str):
-            await self._handle_text(message)
+            await handleTextMessage(self, message)
         elif isinstance(message, bytes):
             await handleAudioMessage(self, message)
 
-    async def _handle_text(self, message):
-        """处理文本消息"""
-        self.logger.info(f"收到文本消息：{message}")
-        try:
-            msg_json = json.loads(message)
-            if msg_json["type"] == "hello":
-                await handleHelloMessage(self, "你好")
-            if msg_json["type"] == "abort":
-                await handleAbortMessage(self)
-        except json.JSONDecodeError:
-            await handleTextMessage(self, message)
-
     def _initialize_components(self):
         self.prompt = self.config["prompt"]
         # 赋予LLM时间观念

core/handle/audioHandle.py

@@ -11,7 +11,10 @@ async def handleAudioMessage(conn, audio):
     if not conn.asr_server_receive:
         logger.debug(f"前期数据处理中，暂停接收")
         return
-    have_voice = conn.vad.is_vad(conn, audio)
+    if conn.client_listen_mode == "auto":
+        have_voice = conn.vad.is_vad(conn, audio)
+    else:
+        have_voice = conn.client_have_voice
 
     # 如果本次没有声音，本段也没声音，就把声音丢弃了
     if have_voice == False and conn.client_have_voice == False:
@@ -26,25 +29,28 @@ async def handleAudioMessage(conn, audio):
         logger.info(f"识别文本: {text}")
         text_len = remove_punctuation_and_length(text)
         if text_len > 0:
-            stt_text = get_string_no_punctuation_or_emoji(text)
+            await startToChat(conn, text)
-            await conn.websocket.send(json.dumps({
-                "type": "stt",
-                "text": stt_text,
-                "session_id": conn.session_id}
-            ))
-            await conn.websocket.send(
-                json.dumps({
-                    "type": "llm",
-                    "text": "😊",
-                    "emotion": "happy",
-                    "session_id": conn.session_id}
-                ))
-            conn.executor.submit(conn.chat, text)
         else:
             conn.asr_server_receive = True
         conn.asr_audio.clear()
         conn.reset_vad_states()
 
+async def startToChat(conn, text):
+    stt_text = get_string_no_punctuation_or_emoji(text)
+    await conn.websocket.send(json.dumps({
+        "type": "stt",
+        "text": stt_text,
+        "session_id": conn.session_id}
+    ))
+    await conn.websocket.send(
+        json.dumps({
+            "type": "llm",
+            "text": "😊",
+            "emotion": "happy",
+            "session_id": conn.session_id}
+        ))
+    conn.executor.submit(conn.chat, text)
+
 
 async def sendAudioMessage(conn, audios, duration, text):
     base_delay = conn.tts_duration

core/handle/textHandle.py

@@ -1,7 +1,37 @@
 import logging
+import json
+from core.handle.abortHandle import handleAbortMessage
+from core.handle.helloHandle import handleHelloMessage
+from core.handle.audioHandle import startToChat
 
 logger = logging.getLogger(__name__)
 
 
 async def handleTextMessage(conn, message):
+    """处理文本消息"""
+    logger.info(f"收到文本消息：{message}")
+    try:
+        msg_json = json.loads(message)
+        if msg_json["type"] == "hello":
+            await handleHelloMessage(conn, "你好")
+        elif msg_json["type"] == "abort":
+            await handleAbortMessage(conn)
+        elif msg_json["type"] == "listen":
+            if "mode" in msg_json:
+                conn.client_listen_mode = msg_json["mode"]
+                logger.info(f"客户端拾音模式：{conn.client_listen_mode}")
+            if msg_json["state"] == "start":
+                conn.client_have_voice = True
+                conn.client_voice_stop = False
+            elif msg_json["state"] == "stop":
+                conn.client_have_voice = True
+                conn.client_voice_stop = True
+            elif msg_json["state"] == "detect":
+                conn.asr_server_receive = False
+                conn.client_have_voice = False
+                conn.asr_audio.clear()
+                if "text" in msg_json:
+                    await startToChat(conn, msg_json["text"])
+    except json.JSONDecodeError:
+        await handleTextMessage(conn, message)
     await conn.websocket.send(message)