update:优化公共方法

main/xiaozhi-server/core/providers/asr/aliyun.py

@@ -155,12 +155,6 @@ class ASRProvider(ASRProviderBase):
         #              f"剩余 {remaining:.2f}秒")
         return time.time() > self.expire_time
 
-    def generate_filename(self, extension=".wav"):
-        return os.path.join(
-            self.output_file,
-            f"tts-{__name__}{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
-        )
-
     def _construct_request_url(self) -> str:
         """构造请求URL，包含参数"""
         request = f"{self.base_url}?appkey={self.app_key}"

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

@@ -8,61 +8,74 @@ import requests
 from datetime import datetime
 from core.providers.tts.base import TTSProviderBase
 
-import http.client
-import urllib.parse
 import time
 import uuid
 from urllib import parse
+
+
 class AccessToken:
     @staticmethod
     def _encode_text(text):
         encoded_text = parse.quote_plus(text)
-        return encoded_text.replace('+', '%20').replace('*', '%2A').replace('%7E', '~')
-    
+        return encoded_text.replace("+", "%20").replace("*", "%2A").replace("%7E", "~")
+
     @staticmethod
     def _encode_dict(dic):
         keys = dic.keys()
         dic_sorted = [(key, dic[key]) for key in sorted(keys)]
         encoded_text = parse.urlencode(dic_sorted)
-        return encoded_text.replace('+', '%20').replace('*', '%2A').replace('%7E', '~')
-    
+        return encoded_text.replace("+", "%20").replace("*", "%2A").replace("%7E", "~")
+
     @staticmethod
     def create_token(access_key_id, access_key_secret):
-        parameters = {'AccessKeyId': access_key_id,
-                      'Action': 'CreateToken',
-                      'Format': 'JSON',
-                      'RegionId': 'cn-shanghai',
-                      'SignatureMethod': 'HMAC-SHA1',
-                      'SignatureNonce': str(uuid.uuid1()),
-                      'SignatureVersion': '1.0',
-                      'Timestamp': time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime()),
-                      'Version': '2019-02-28'}
+        parameters = {
+            "AccessKeyId": access_key_id,
+            "Action": "CreateToken",
+            "Format": "JSON",
+            "RegionId": "cn-shanghai",
+            "SignatureMethod": "HMAC-SHA1",
+            "SignatureNonce": str(uuid.uuid1()),
+            "SignatureVersion": "1.0",
+            "Timestamp": time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime()),
+            "Version": "2019-02-28",
+        }
         # 构造规范化的请求字符串
         query_string = AccessToken._encode_dict(parameters)
         # print('规范化的请求字符串: %s' % query_string)
         # 构造待签名字符串
-        string_to_sign = 'GET' + '&' + AccessToken._encode_text('/') + '&' + AccessToken._encode_text(query_string)
+        string_to_sign = (
+            "GET"
+            + "&"
+            + AccessToken._encode_text("/")
+            + "&"
+            + AccessToken._encode_text(query_string)
+        )
         # print('待签名的字符串: %s' % string_to_sign)
         # 计算签名
-        secreted_string = hmac.new(bytes(access_key_secret + '&', encoding='utf-8'),
-                                   bytes(string_to_sign, encoding='utf-8'),
-                                   hashlib.sha1).digest()
+        secreted_string = hmac.new(
+            bytes(access_key_secret + "&", encoding="utf-8"),
+            bytes(string_to_sign, encoding="utf-8"),
+            hashlib.sha1,
+        ).digest()
         signature = base64.b64encode(secreted_string)
         # print('签名: %s' % signature)
         # 进行URL编码
         signature = AccessToken._encode_text(signature)
         # print('URL编码后的签名: %s' % signature)
         # 调用服务
-        full_url = 'http://nls-meta.cn-shanghai.aliyuncs.com/?Signature=%s&%s' % (signature, query_string)
+        full_url = "http://nls-meta.cn-shanghai.aliyuncs.com/?Signature=%s&%s" % (
+            signature,
+            query_string,
+        )
         # print('url: %s' % full_url)
         # 提交HTTP GET请求
         response = requests.get(full_url)
         if response.ok:
             root_obj = response.json()
-            key = 'Token'
+            key = "Token"
             if key in root_obj:
-                token = root_obj[key]['Id']
-                expire_time = root_obj[key]['ExpireTime']
+                token = root_obj[key]["Id"]
+                expire_time = root_obj[key]["ExpireTime"]
                 return token, expire_time
         # print(response.text)
         return None, None
@@ -70,10 +83,9 @@ class AccessToken:
 
 class TTSProvider(TTSProviderBase):
 
-
     def __init__(self, config, delete_audio_file):
         super().__init__(config, delete_audio_file)
-        
+
         # 新增空值判断逻辑
         self.access_key_id = config.get("access_key_id")
         self.access_key_secret = config.get("access_key_secret")
@@ -87,9 +99,7 @@ class TTSProvider(TTSProviderBase):
         self.pitch_rate = config.get("pitch_rate", 0)
         self.host = config.get("host", "nls-gateway-cn-shanghai.aliyuncs.com")
         self.api_url = f"https://{self.host}/stream/v1/tts"
-        self.header = {
-            "Content-Type": "application/json"
-        }
+        self.header = {"Content-Type": "application/json"}
 
         if self.access_key_id and self.access_key_secret:
             # 使用密钥对生成临时token
@@ -99,35 +109,30 @@ class TTSProvider(TTSProviderBase):
             self.token = config.get("token")
             self.expire_time = None
 
-  
     def _refresh_token(self):
         """刷新Token并记录过期时间"""
         if self.access_key_id and self.access_key_secret:
             self.token, expire_time_str = AccessToken.create_token(
-                self.access_key_id, 
-                self.access_key_secret
+                self.access_key_id, self.access_key_secret
             )
             if not expire_time_str:
                 raise ValueError("无法获取有效的Token过期时间")
 
             try:
-                #统一转换为字符串处理
+                # 统一转换为字符串处理
                 expire_str = str(expire_time_str).strip()
 
                 if expire_str.isdigit():
                     expire_time = datetime.fromtimestamp(int(expire_str))
                 else:
-                    expire_time = datetime.strptime(
-                        expire_str, 
-                        "%Y-%m-%dT%H:%M:%SZ"
-                    )
+                    expire_time = datetime.strptime(expire_str, "%Y-%m-%dT%H:%M:%SZ")
                 self.expire_time = expire_time.timestamp() - 60
             except Exception as e:
                 raise ValueError(f"无效的过期时间格式: {expire_str}") from e
-        
+
         else:
             self.expire_time = None
-            
+
         if not self.token:
             raise ValueError("无法获取有效的访问Token")
 
@@ -142,8 +147,6 @@ class TTSProvider(TTSProviderBase):
         #              f"过期时间 {datetime.fromtimestamp(self.expire_time)} | "
         #              f"剩余 {remaining:.2f}秒")
         return time.time() > self.expire_time
-    def generate_filename(self, extension=".wav"):
-        return os.path.join(self.output_file, f"tts-{__name__}{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
 
     async def text_to_speak(self, text, output_file):
         if self._is_token_expired():
@@ -158,21 +161,27 @@ class TTSProvider(TTSProviderBase):
             "voice": self.voice,
             "volume": self.volume,
             "speech_rate": self.speech_rate,
-            "pitch_rate": self.pitch_rate
+            "pitch_rate": self.pitch_rate,
         }
 
         # print(self.api_url, json.dumps(request_json, ensure_ascii=False))
         try:
-            resp = requests.post(self.api_url, json.dumps(request_json), headers=self.header)
+            resp = requests.post(
+                self.api_url, json.dumps(request_json), headers=self.header
+            )
             if resp.status_code == 401:  # Token过期特殊处理
                 self._refresh_token()
-                resp = requests.post(self.api_url, json.dumps(request_json), headers=self.header)
+                resp = requests.post(
+                    self.api_url, json.dumps(request_json), headers=self.header
+                )
             # 检查返回请求数据的mime类型是否是audio/***，是则保存到指定路径下；返回的是binary格式的
-            if resp.headers['Content-Type'].startswith('audio/'):
-                with open(output_file, 'wb') as f:
+            if resp.headers["Content-Type"].startswith("audio/"):
+                with open(output_file, "wb") as f:
                     f.write(resp.content)
                 return output_file
             else:
-                raise Exception(f"{__name__} status_code: {resp.status_code} response: {resp.content}")
+                raise Exception(
+                    f"{__name__} status_code: {resp.status_code} response: {resp.content}"
+                )
         except Exception as e:
             raise Exception(f"{__name__} error: {e}")

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

@@ -3,6 +3,7 @@ from config.logger import setup_logging
 import queue
 import os
 import uuid
+import datetime
 import threading
 from core.utils import p3
 from core.utils import textUtils
@@ -57,9 +58,11 @@ class TTSProviderBase(ABC):
         self.processed_chars = 0
         self.is_first_sentence = True
 
-    @abstractmethod
-    def generate_filename(self):
-        pass
+    def generate_filename(self, extension=".wav"):
+        return os.path.join(
+            self.output_file,
+            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
+        )
 
     def to_tts(self, text):
         tmp_file = self.generate_filename()
@@ -148,7 +151,7 @@ class TTSProviderBase(ABC):
         self.tts_timeout = conn.config.get("tts_timeout", 10)
         # tts 消化线程
         self.tts_priority_thread = threading.Thread(
-            target=self._tts_text_priority_thread, daemon=True
+            target=self.tts_text_priority_thread, daemon=True
         )
         self.tts_priority_thread.start()
 
@@ -160,7 +163,7 @@ class TTSProviderBase(ABC):
 
     # 这里默认是非流式的处理方式
     # 流式处理方式请在子类中重写
-    def _tts_text_priority_thread(self):
+    def tts_text_priority_thread(self):
         while not self.conn.stop_event.is_set():
             try:
                 message = self.tts_text_queue.get(timeout=1)
@@ -219,9 +222,6 @@ class TTSProviderBase(ABC):
                     self.conn.loop,
                 )
                 result = future.result()
-                logger.bind(tag=TAG).info(
-                    f"audio_play_priority result: {text} {result}"
-                )
             except Exception as e:
                 logger.bind(tag=TAG).error(
                     f"audio_play_priority priority_thread: {text} {e}"

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

@@ -21,12 +21,6 @@ class TTSProvider(TTSProviderBase):
         self.host = "api.coze.cn"
         self.api_url = f"https://{self.host}/v1/audio/speech"
 
-    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_json = {
             "model": self.model,
@@ -47,4 +41,4 @@ class TTSProvider(TTSProviderBase):
             file_to_save = open(output_file, "wb")
             file_to_save.write(data)
         except Exception as e:
-            raise Exception(f"{__name__} error: {e}")
+            raise Exception(f"{__name__} error: {e}")

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

@@ -41,12 +41,6 @@ class TTSProvider(TTSProviderBase):
         self.header = {"Authorization": f"{self.authorization}{self.access_token}"}
         check_model_key("TTS", self.access_token)
 
-    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_json = {
             "app": {

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

@@ -133,12 +133,6 @@ class TTSProvider(TTSProviderBase):
         self.seed = int(config.get("seed")) if config.get("seed") else None
         self.api_url = config.get("api_url", "http://127.0.0.1:8080/v1/tts")
 
-    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):
         # Prepare reference data
         byte_audios = [audio_to_bytes(ref_audio) for ref_audio in self.reference_audio]

main/xiaozhi-server/core/providers/tts/gpt_sovits_v2.py

@@ -71,12 +71,6 @@ class TTSProvider(TTSProviderBase):
             config.get("aux_ref_audio_paths")
         )
 
-    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_json = {
             "text": text,

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

@@ -36,12 +36,6 @@ class TTSProvider(TTSProviderBase):
         self.inp_refs = parse_string_to_list(config.get("inp_refs"))
         self.if_sr = str(config.get("if_sr", False)).lower() in ("true", "1", "yes")
 
-    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 = {
             "refer_wav_path": self.refer_wav_path,
@@ -67,4 +61,3 @@ class TTSProvider(TTSProviderBase):
             error_msg = f"GPT_SoVITS_V3 TTS请求失败: {resp.status_code} - {resp.text}"
             logger.bind(tag=TAG).error(error_msg)
             raise Exception(error_msg)
-

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

@@ -8,6 +8,7 @@ import websockets
 from datetime import datetime
 from config.logger import setup_logging
 from core.providers.tts.base import TTSProviderBase
+from core.providers.tts.dto.dto import TTSMessageDTO, SentenceType, ContentType
 from core.utils.util import pcm_to_data
 
 TAG = __name__
@@ -149,43 +150,6 @@ class TTSProvider(TTSProviderBase):
         self.start_connection_flag = False
         self.tts_text = ""
 
-    async def open_audio_channels(self, conn):
-        await super().open_audio_channels(conn)
-        ws_header = {
-            "X-Api-App-Key": self.appId,
-            "X-Api-Access-Key": self.access_token,
-            "X-Api-Resource-Id": self.resource_id,
-            "X-Api-Connect-Id": uuid.uuid4(),
-        }
-        self.ws = await websockets.connect(
-            self.ws_url, additional_headers=ws_header, max_size=1000000000
-        )
-        tts_priority = threading.Thread(
-            target=self._start_monitor_tts_response_thread, daemon=True
-        )
-        tts_priority.start()
-
-    def generate_filename(self, extension=".wav"):
-        return os.path.join(
-            self.output_file,
-            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
-        )
-
-    def to_tts(self, text):
-        future = asyncio.run_coroutine_threadsafe(
-            self.start_session(self.conn.sentence_id), loop=self.conn.loop
-        )
-        future.result()
-        future = asyncio.run_coroutine_threadsafe(
-            self.text_to_speak(text, None), loop=self.conn.loop
-        )
-        future.result()
-        future = asyncio.run_coroutine_threadsafe(
-            self.finish_session(self.conn.sentence_id), loop=self.conn.loop
-        )
-        future.result()
-        return self.interface_type.value
-
     async def send_event(
         self, header: bytes, optional: bytes | None = None, payload: bytes = None
     ):
@@ -360,14 +324,65 @@ class TTSProvider(TTSProviderBase):
             self.start_connection_flag = False
         await self.start_connection()
         self.start_connection_flag = True
-        await super().reset()
 
     async def close(self):
-        super().close()
         """资源清理方法"""
         await self.finish_connection()
         await self.ws.close()
 
+    ###################################################################################
+    # 以下是火山双流式TTS重写父类的方法
+    ###################################################################################
+
+    async def open_audio_channels(self, conn):
+        await super().open_audio_channels(conn)
+        ws_header = {
+            "X-Api-App-Key": self.appId,
+            "X-Api-Access-Key": self.access_token,
+            "X-Api-Resource-Id": self.resource_id,
+            "X-Api-Connect-Id": uuid.uuid4(),
+        }
+        self.ws = await websockets.connect(
+            self.ws_url, additional_headers=ws_header, max_size=1000000000
+        )
+        tts_priority = threading.Thread(
+            target=self._start_monitor_tts_response_thread, daemon=True
+        )
+        tts_priority.start()
+
+    def tts_text_priority_thread(self):
+        while not self.conn.stop_event.is_set():
+            try:
+                message = self.tts_text_queue.get(timeout=1)
+                if message.sentence_type == SentenceType.FIRST:
+                    # 初始化参数
+                    future = asyncio.run_coroutine_threadsafe(
+                        self.start_session(self.conn.sentence_id), loop=self.conn.loop
+                    )
+                    future.result()
+                elif ContentType.TEXT == message.content_type:
+                    if message.content_detail:
+                        future = asyncio.run_coroutine_threadsafe(
+                            self.text_to_speak(message.content_detail, None),
+                            loop=self.conn.loop,
+                        )
+                        future.result()
+                elif ContentType.FILE == message.content_type:
+                    pass
+
+                if message.sentence_type == SentenceType.LAST:
+                    future = asyncio.run_coroutine_threadsafe(
+                        self.finish_session(self.conn.sentence_id), loop=self.conn.loop
+                    )
+                    future.result()
+
+            except queue.Empty:
+                continue
+            except Exception as e:
+                logger.bind(tag=TAG).error(
+                    f"处理TTS文本失败: {str(e)}, 类型: {type(e).__name__}, 堆栈: {traceback.format_exc()}"
+                )
+
     async def text_to_speak(self, text, _):
         # 发送文本
         await self.send_text(self.speaker, text, self.conn.sentence_id)

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

@@ -29,12 +29,6 @@ class TTSProvider(TTSProviderBase):
         self.output_file = config.get("output_dir", "tmp/")
         check_model_key("TTS", self.api_key)
 
-    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):
         headers = {
             "Authorization": f"Bearer {self.api_key}",

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

@@ -22,12 +22,6 @@ class TTSProvider(TTSProviderBase):
         self.host = "api.siliconflow.cn"
         self.api_url = f"https://{self.host}/v1/audio/speech"
 
-    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_json = {
             "model": self.model,
@@ -47,4 +41,4 @@ class TTSProvider(TTSProviderBase):
             file_to_save = open(output_file, "wb")
             file_to_save.write(data)
         except Exception as e:
-            raise Exception(f"{__name__} error: {e}")
+            raise Exception(f"{__name__} error: {e}")

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

@@ -121,12 +121,6 @@ class TTSProvider(TTSProviderBase):
             msg = msg.encode("utf-8")
         return hmac.new(key, msg, hashlib.sha256).digest()
 
-    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):
         # 构建请求体
         request_json = {