部分TTS参数调整

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

@@ -8,6 +8,10 @@ logger = setup_logging()
 
 
 class TTSProvider(TTSProviderBase):
+    TTS_PARAM_CONFIG = [
+        ("ttsRate", "speed", 0.25, 4, 1, lambda v: round(float(v), 2)),
+    ]
+
     def __init__(self, config, delete_audio_file):
         super().__init__(config, delete_audio_file)
         self.api_key = config.get("api_key")
@@ -17,13 +21,15 @@ class TTSProvider(TTSProviderBase):
             self.voice = config.get("private_voice")
         else:
             self.voice = config.get("voice", "alloy")
-        self.response_format = config.get("format", "wav")
         self.audio_file_type = config.get("format", "wav")
 
         # 处理空字符串的情况
         speed = config.get("speed", "1.0")
         self.speed = float(speed) if speed else 1.0
 
+        # 应用百分比调整（如果存在），否则使用公有化配置
+        self._apply_percentage_params(config)
+
         self.output_file = config.get("output_dir", "tmp/")
         model_key_msg = check_model_key("TTS", self.api_key)
         if model_key_msg:
@@ -38,7 +44,7 @@ class TTSProvider(TTSProviderBase):
             "model": self.model,
             "input": text,
             "voice": self.voice,
-            "response_format": "wav",
+            "response_format": self.audio_file_type,
             "speed": self.speed,
         }
         response = requests.post(self.api_url, json=data, headers=headers)