Block docker web (#248)

* update:docker智控台设置提示

* 修复启动报错问题 (#247)

修复启动时SyntaxWarning: invalid escape sequence '\]'
  half_width_punctuations = '!"#$%&\'()*+,-./:;<=>?@[\]^_`{|}~'的报错问题

* 2025-3-8-iot状态更新 (#243)

* 添加 GPTSoVits-V3 TTS (#234)

---------

Co-authored-by: hrz <1710360675@qq.com>
Co-authored-by: vonweller <154695311+vonweller@users.noreply.github.com>
Co-authored-by: Jiao Haoyang <108573524+XuSenfeng@users.noreply.github.com>
Co-authored-by: Echo <yowfung@163.com>

main/xiaozhi-server/config.yaml

@@ -37,7 +37,8 @@ log:
   data_dir: data
 iot:
   Speaker:
-    volume: 100
+    # 设置esp32的音量，范围0-100
+    volume: 80
 xiaozhi:
   type: hello
   version: 1
@@ -258,6 +259,21 @@ TTS:
     parallel_infer: true
     repetition_penalty: 1.35
     aux_ref_audio_paths: []
+  GPT_SOVITS_V3:
+    type: gpt_sovits_v3
+    url: "http://127.0.0.1:9880/tts"
+    output_file: tmp/
+    text_lang: "auto"
+    ref_audio_path: "caixukun.wav"
+    prompt_lang: "zh"
+    prompt_text: ""
+    top_k: 5
+    top_p: 1
+    temperature: 1
+    sample_steps: 16
+    media_type: "wav"
+    streaming_mode: false
+    threshold: 30
   MinimaxTTS:
     # Minimax语音合成服务，需要先在minimax平台创建账户充值，并获取登录信息
     # 平台地址：https://platform.minimaxi.com/

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

@@ -109,7 +109,48 @@ async def handleIotDescriptors(conn, descriptors):
         default_iot_volume = conn.config["iot"]["Speaker"]["volume"]
     logger.bind(tag=TAG).info(f"服务端设置音量为{default_iot_volume}")
     await send_iot_conn(conn, "Speaker", "SetVolume", {"volume": default_iot_volume})
+async def handleIotStatus(conn, states):
+    """
+    处理物联网状态
+    示例: [{
+        "name":"Speaker",
+        "state":{
+            "volume":100
+        }
+    }]
+    states: 状态列表
+    """
+    for state in states:
+        for key, value in conn.iot_descriptors.items():
+            if key == state["name"]:
+                for property_item in value.properties:
+                    # properties为字典列表, 记录各种属性
+                    for k, v in state["state"].items():
+                        # state为字典, 记录各种属性的值, 是需要记录的信息
+                        if property_item["name"] == k:
+                            # 检查一下属性是不是相同的
+                            if type(v) != type(property_item["value"]):
+                                logger.bind(tag=TAG).error(f"属性{property_item['name']}的值类型不匹配")
+                                break
+                            else:
+                                property_item["value"] = v
+                                logger.bind(tag=TAG).info(f"物联网状态更新: {key} , {property_item['name']} = {v}")
+                            break
+                break
 
+async def get_iot_status(conn, name, property_name):
+    """
+    获取物联网状态
+    name: 设备名称 "Speaker"
+    property_name: 属性名称 "volume"
+    返回值: 属性值, 实际的属性有int, bool和str三种类型
+    """
+    for key, value in conn.iot_descriptors.items():
+        if key == name:
+            for property_item in value.properties:
+                if property_item["name"] == property_name:
+                    return property_item["value"]
+    return None
 
 async def send_iot_conn(conn, name, method_name, parameters):
     """

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

@@ -3,7 +3,7 @@ import json
 from core.handle.abortHandle import handleAbortMessage
 from core.handle.helloHandle import handleHelloMessage
 from core.handle.receiveAudioHandle import startToChat
-from core.handle.iotHandle import handleIotDescriptors
+from core.handle.iotHandle import handleIotDescriptors, handleIotStatus
 
 TAG = __name__
 logger = setup_logging()
@@ -40,5 +40,7 @@ async def handleTextMessage(conn, message):
         elif msg_json["type"] == "iot":
             if "descriptors" in msg_json:
                 await handleIotDescriptors(conn, msg_json["descriptors"])
+            if "states" in msg_json:
+                await handleIotStatus(conn, msg_json["states"])  
     except json.JSONDecodeError:
         await conn.websocket.send(message)

main/xiaozhi-server/core/providers/tts/gpt_sovits_v3.py

@@ -0,0 +1,52 @@
+import os
+import uuid
+import requests
+from config.logger import setup_logging
+from datetime import datetime
+from core.providers.tts.base import TTSProviderBase
+
+TAG = __name__
+logger = setup_logging()
+
+class TTSProvider(TTSProviderBase):
+    def __init__(self, config, delete_audio_file):
+        super().__init__(config, delete_audio_file)
+        self.url = config.get("url")
+        self.text_lang = config.get("text_lang", "audo")
+        self.ref_audio_path = config.get("ref_audio_path")
+        self.prompt_lang = config.get("prompt_lang")
+        self.prompt_text = config.get("prompt_text")
+        self.top_k = config.get("top_k", 5)
+        self.top_p = config.get("top_p", 1)
+        self.temperature = config.get("temperature", 1)
+        self.sample_steps = config.get("sample_steps", 16)
+        self.media_type = config.get("media_type", "wav")
+        self.streaming_mode = config.get("streaming_mode", False)
+        self.threshold = config.get("threshold", 30)
+
+
+    def generate_filename(self, extension=".wav"):
+        return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
+
+    async def text_to_speak(self, text, output_file):
+        request_params = {
+            "text": text,
+            "text_lang": self.text_lang,
+            "ref_audio_path": self.ref_audio_path,
+            "prompt_lang": self.prompt_lang,
+            "prompt_text": self.prompt_text,
+            "top_k": self.top_k,
+            "top_p": self.top_p,
+            "temperature": self.temperature,
+            "sample_steps": self.sample_steps,
+            "media_type": self.media_type,
+            "streaming_mode": self.streaming_mode,
+            "threshold": self.threshold,
+        }
+
+        resp = requests.get(self.url, params=request_params)
+        if resp.status_code == 200:
+            with open(output_file, "wb") as file:
+                file.write(resp.content)
+        else:
+            logger.bind(tag=TAG).error(f"GPT_SoVITS_V3 TTS请求失败: {resp.status_code} - {resp.text}")

main/xiaozhi-server/core/utils/util.py

@@ -75,7 +75,7 @@ def get_string_no_punctuation_or_emoji(s):
 def remove_punctuation_and_length(text):
     # 全角符号和半角符号的Unicode范围
     full_width_punctuations = '！＂＃＄％＆＇（）＊＋，－。／：；＜＝＞？＠［＼］＾＿｀｛｜｝～'
-    half_width_punctuations = '!"#$%&\'()*+,-./:;<=>?@[\]^_`{|}~'
+    half_width_punctuations = r'!"#$%&\'()*+,-./:;<=>?@[\]^_`{|}~'
     space = ' '  # 半角空格
     full_width_space = '　'  # 全角空格
 

main/xiaozhi-server/docker-compose.yml

@@ -21,17 +21,18 @@ services:
       - ./data:/opt/xiaozhi-esp32-server/data
       # 模型文件挂接，很重要
       - ./models/SenseVoiceSmall/model.pt:/opt/xiaozhi-esp32-server/models/SenseVoiceSmall/model.pt
-  xiaozhi-esp32-server-web:
-    image: ghcr.nju.edu.cn/xinnan-tech/xiaozhi-esp32-server:web_latest
-    container_name: xiaozhi-esp32-server-web
-    restart: always
-    ports:
-      - "8002:8002"
-    environment:
-      - TZ=Asia/Shanghai
-      ##记得改mysql和redis IP 密码
-      - SPRING_DATASOURCE_DRUID_URL=jdbc:mysql://192.168.1.20:3306/xiaozhi_esp32_server?useUnicode=true&characterEncoding=UTF-8&serverTimezone=Asia/Shanghai
-      - SPRING_DATASOURCE_DRUID_USERNAME=root
-      - SPRING_DATASOURCE_DRUID_PASSWORD=123456
-      - SPRING_DATA_REDIS_HOST=192.168.1.20
-      - SPRING_DATA_REDIS_PORT=6379
+#  #智控台还没开发好，还不能完全使用，会报很多错误，如果是非技术人员，请不要启用智控台服务
+#  xiaozhi-esp32-server-web:
+#    image: ghcr.nju.edu.cn/xinnan-tech/xiaozhi-esp32-server:web_latest
+#    container_name: xiaozhi-esp32-server-web
+#    restart: always
+#    ports:
+#      - "8002:8002"
+#    environment:
+#      - TZ=Asia/Shanghai
+#      ##记得改mysql和redis IP 密码
+#      - SPRING_DATASOURCE_DRUID_URL=jdbc:mysql://192.168.1.20:3306/xiaozhi_esp32_server?useUnicode=true&characterEncoding=UTF-8&serverTimezone=Asia/Shanghai
+#      - SPRING_DATASOURCE_DRUID_USERNAME=root
+#      - SPRING_DATASOURCE_DRUID_PASSWORD=123456
+#      - SPRING_DATA_REDIS_HOST=192.168.1.20
+#      - SPRING_DATA_REDIS_PORT=6379