Merge pull request #476 from journey-ad/optional-greeting

优化打招呼和进入聆听模式的反馈

.gitignore

@@ -145,6 +145,7 @@ tmp
 .history
 .DS_Store
 main/xiaozhi-server/data
+!main/xiaozhi-server/data/tts_notify.mp3
 main/manager-web/node_modules
 .config.yaml
 .secrets.yaml

main/xiaozhi-server/config.yaml

@@ -57,6 +57,10 @@ delete_audio: true
 close_connection_no_voice_time: 120
 # TTS请求超时时间(秒)
 tts_timeout: 10
+# TTS播放结束提示音
+tts_notify: "data/tts_notify.mp3"
+# 开场是否回复唤醒词
+enable_greeting: true
 
 CMD_exit:
   - "退出"

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

@@ -60,9 +60,19 @@ 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":
+        # 清除服务端讲话状态
         conn.clearSpeakStatus()
+        # 播放提示音
+        tts_notify = conn.config.get("tts_notify", "")
+        if tts_notify:
+            opus_packets, duration = conn.tts.audio_to_opus_data(tts_notify)
+            for opus_packet in opus_packets:
+                await conn.websocket.send(opus_packet)
+
+    # 发送消息到客户端
+    await conn.websocket.send(json.dumps(message))
 
 
 async def send_stt_message(conn, text):

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

@@ -3,6 +3,7 @@ import json
 from core.handle.abortHandle import handleAbortMessage
 from core.handle.helloHandle import handleHelloMessage
 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 +39,13 @@ 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"])
+                    if conn.config.get("enable_greeting", True):
+                        # 启用开场白 通过llm回复唤醒词
+                        await startToChat(conn, msg_json["text"])
+                    else:
+                        # 不启用 直接转为聆听状态
+                        await send_stt_message(conn, msg_json["text"])
+                        await send_tts_message(conn, "stop", None)
         elif msg_json["type"] == "iot":
             if "descriptors" in msg_json:
                 await handleIotDescriptors(conn, msg_json["descriptors"])