feat:VITS 格式更新为 OGG

App/Event.py

@@ -8,7 +8,9 @@
 import random
 import re
 import time
+from io import BytesIO
 from typing import Union
+
 from loguru import logger
 
 import openai_async
@@ -102,7 +104,10 @@ async def TTS_Support_Check(text, user_id):
                                                         params=TTS_REQ(task_id=user_id,
                                                                        text=_new_text,
                                                                        model_name=_vits_config["model_name"],
-                                                                       speaker_id=_vits_config["speaker_id"]))
+                                                                       speaker_id=_vits_config["speaker_id"],
+                                                                       audio_type="ogg"
+                                                                       ))
+
         if not result:
             logger.error(f"TTS:{user_id} --type:vits --content: {text}:{len(text)} --{e}")
             return

README.EN.md

@@ -227,7 +227,7 @@ that are not in the preset will not be completed.
 - auzre:location Server resource address
 - auzre:key api key
 
-#### VITS Voice Support Description(ONLY CN NOW)
+#### VITS Voice Support Description(Language types are determined by the model)
 
 This technology provides an emulated voice interaction technique.
 

README.md

@@ -224,7 +224,7 @@ https://azure.microsoft.com/en-us/pricing/details/cognitive-services/speech-serv
 - auzre:location 服务器资源地址
 - auzre:key api key
 
-#### VITS 语音支持说明(ONLY CN NOW)
+#### VITS 语音支持说明(ONLY CN/JA NOW)
 
 Api 后端请使用我打包改造的 MoeGoe https://github.com/sudoskys/MoeGoe 本机运行
 

utils/TTS.py

@@ -16,6 +16,7 @@ class TTS_REQ(BaseModel):
     task_id: int = 1
     text: str = "[ZH]你好[ZH]"
     speaker_id: int = 0
+    audio_type: str = "ogg"
 
 
 class TTS_Clint(object):