fix：aliyun,cozecn,custom,doubao,gpt_sovits_v2,gpt_sovits_v3,minimax,openai,siliconflow,ttson,这些tts兼容

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

@@ -2,7 +2,11 @@ import os
 import uuid
 import requests
 from datetime import datetime
+
+from pydub import AudioSegment
+
 from core.providers.tts.base import TTSProviderBase
+from core.providers.tts.dto.dto import TTSMessageDTO, MsgType, SentenceType
 
 
 class TTSProvider(TTSProviderBase):
@@ -22,7 +26,8 @@ class TTSProvider(TTSProviderBase):
     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):
+    async def text_to_speak(self, u_id, text, is_last_text=False, is_first_text=False):
+        tmp_file = self.generate_filename()
         request_json = {
             "model": self.model,
             "input": text,
@@ -35,5 +40,17 @@ class TTSProvider(TTSProviderBase):
         }
         response = requests.request("POST", self.api_url, json=request_json, headers=headers)
         data = response.content
-        file_to_save = open(output_file, "wb")
+        file_to_save = open(tmp_file, "wb")
         file_to_save.write(data)
+        # 使用 pydub 读取临时文件
+        audio = AudioSegment.from_file(tmp_file, format="wav")
+        audio = audio.set_channels(1).set_frame_rate(16000)
+        opus_datas = self.wav_to_opus_data_audio_raw(audio.raw_data)
+        yield TTSMessageDTO(u_id=u_id, msg_type=MsgType.TTS_TEXT_RESPONSE, content=opus_datas, tts_finish_text=text,
+                            sentence_type=SentenceType.SENTENCE_START)
+        # 用完后删除临时文件
+        try:
+            os.remove(tmp_file)
+        except FileNotFoundError:
+            # 若文件不存在，忽略该异常
+            pass