update:合并main分支

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

@@ -14,17 +14,23 @@ class TTSProvider(TTSProviderBase):
         super().__init__(config, delete_audio_file)
         self.model = config.get("model")
         self.access_token = config.get("access_token")
-        self.voice = config.get("voice")
+        if config.get("private_voice"):
+            self.voice = config.get("private_voice")
+        else:
+            self.voice = config.get("voice")
         self.response_format = config.get("response_format")
         self.sample_rate = config.get("sample_rate")
-        self.speed = config.get("speed")
+        self.speed = float(config.get("speed", 1.0))
         self.gain = config.get("gain")
 
         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}")
+        return os.path.join(
+            self.output_file,
+            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
+        )
 
     async def text_to_speak(self, u_id, text, is_last_text=False, is_first_text=False):
         tmp_file = self.generate_filename()
@@ -36,9 +42,11 @@ class TTSProvider(TTSProviderBase):
         }
         headers = {
             "Authorization": f"Bearer {self.access_token}",
-            "Content-Type": "application/json"
+            "Content-Type": "application/json",
         }
-        response = requests.request("POST", self.api_url, json=request_json, headers=headers)
+        response = requests.request(
+            "POST", self.api_url, json=request_json, headers=headers
+        )
         data = response.content
         file_to_save = open(tmp_file, "wb")
         file_to_save.write(data)
@@ -46,8 +54,13 @@ class TTSProvider(TTSProviderBase):
         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)
+        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)