fix:manager下发配置字符转数字bug

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

@@ -89,19 +89,19 @@ class TTSProvider(TTSProviderBase):
         self.reference_audio = config.get("reference_audio", [])
         self.reference_text = config.get("reference_text", [])
         self.format = config.get("format", "wav")
-        self.channels = config.get("channels", 1)
-        self.rate = config.get("rate", 44100)
+        self.channels = int(config.get("channels", 1))
+        self.rate = int(config.get("rate", 44100))
         self.api_key = config.get("api_key", "YOUR_API_KEY")
         have_key = check_model_key("FishSpeech TTS", self.api_key)
         if not have_key:
             return
         self.normalize = config.get("normalize", True)
-        self.max_new_tokens = config.get("max_new_tokens", 1024)
-        self.chunk_length = config.get("chunk_length", 200)
-        self.top_p = config.get("top_p", 0.7)
-        self.repetition_penalty = config.get("repetition_penalty", 1.2)
-        self.temperature = config.get("temperature", 0.7)
-        self.streaming = config.get("streaming", False)
+        self.max_new_tokens = int(config.get("max_new_tokens", 1024))
+        self.chunk_length = int(config.get("chunk_length", 200))
+        self.top_p = float(config.get("top_p", 0.7))
+        self.repetition_penalty = float(config.get("repetition_penalty", 1.2))
+        self.temperature = float(config.get("temperature", 0.7))
+        self.streaming = bool(config.get("streaming", False))
         self.use_memory_cache = config.get("use_memory_cache", "on")
         self.seed = config.get("seed")
         self.api_url = config.get("api_url", "http://127.0.0.1:8080/v1/tts")

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

@@ -10,6 +10,7 @@ from core.providers.tts.base import TTSProviderBase
 TAG = __name__
 logger = setup_logging()
 
+
 class TTSProvider(TTSProviderBase):
     def __init__(self, config, delete_audio_file):
         super().__init__(config, delete_audio_file)
@@ -18,23 +19,26 @@ class TTSProvider(TTSProviderBase):
         self.ref_audio_path = config.get("ref_audio_path")
         self.prompt_text = config.get("prompt_text")
         self.prompt_lang = config.get("prompt_lang", "zh")
-        self.top_k = config.get("top_k", 5)
-        self.top_p = config.get("top_p", 1)
-        self.temperature = config.get("temperature", 1)
+        self.top_k = int(config.get("top_k", 5))
+        self.top_p = float(config.get("top_p", 1))
+        self.temperature = float(config.get("temperature", 1))
         self.text_split_method = config.get("text_split_method", "cut0")
-        self.batch_size = config.get("batch_size", 1)
-        self.batch_threshold = config.get("batch_threshold", 0.75)
-        self.split_bucket = config.get("split_bucket", True)
-        self.return_fragment = config.get("return_fragment", False)
-        self.speed_factor = config.get("speed_factor", 1.0)
-        self.streaming_mode = config.get("streaming_mode", False)
-        self.seed = config.get("seed", -1)
-        self.parallel_infer = config.get("parallel_infer", True)
-        self.repetition_penalty = config.get("repetition_penalty", 1.35)
+        self.batch_size = int(config.get("batch_size", 1))
+        self.batch_threshold = float(config.get("batch_threshold", 0.75))
+        self.split_bucket = bool(config.get("split_bucket", True))
+        self.return_fragment = bool(config.get("return_fragment", False))
+        self.speed_factor = float(config.get("speed_factor", 1.0))
+        self.streaming_mode = bool(config.get("streaming_mode", False))
+        self.seed = int(config.get("seed", -1))
+        self.parallel_infer = bool(config.get("parallel_infer", True))
+        self.repetition_penalty = float(config.get("repetition_penalty", 1.35))
         self.aux_ref_audio_paths = 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}")
+        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 = {
@@ -56,7 +60,7 @@ class TTSProvider(TTSProviderBase):
             "streaming_mode": self.streaming_mode,
             "seed": self.seed,
             "parallel_infer": self.parallel_infer,
-            "repetition_penalty": self.repetition_penalty
+            "repetition_penalty": self.repetition_penalty,
         }
 
         resp = requests.post(self.url, json=request_json)
@@ -64,4 +68,6 @@ class TTSProvider(TTSProviderBase):
             with open(output_file, "wb") as file:
                 file.write(resp.content)
         else:
-            logger.bind(tag=TAG).error(f"GPT_SoVITS_V2 TTS请求失败: {resp.status_code} - {resp.text}")
+            logger.bind(tag=TAG).error(
+                f"GPT_SoVITS_V2 TTS请求失败: {resp.status_code} - {resp.text}"
+            )

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

@@ -8,6 +8,7 @@ from core.providers.tts.base import TTSProviderBase
 TAG = __name__
 logger = setup_logging()
 
+
 class TTSProvider(TTSProviderBase):
     def __init__(self, config, delete_audio_file):
         super().__init__(config, delete_audio_file)
@@ -16,18 +17,20 @@ class TTSProvider(TTSProviderBase):
         self.prompt_text = config.get("prompt_text")
         self.prompt_language = config.get("prompt_language")
         self.text_language = config.get("text_language", "audo")
-        self.top_k = config.get("top_k", 15)
-        self.top_p = config.get("top_p", 1.0)
-        self.temperature = config.get("temperature", 1.0)
-        self.cut_punc = config.get("cut_punc","")
-        self.speed = config.get("speed", 1.0)
-        self.inp_refs = config.get("inp_refs",[])
-        self.sample_steps = config.get("sample_steps",32)
-        self.if_sr = config.get("if_sr",False)
-
+        self.top_k = int(config.get("top_k", 15))
+        self.top_p = float(config.get("top_p", 1.0))
+        self.temperature = float(config.get("temperature", 1.0))
+        self.cut_punc = config.get("cut_punc", "")
+        self.speed = float(config.get("speed", 1.0))
+        self.inp_refs = config.get("inp_refs", [])
+        self.sample_steps = int(config.get("sample_steps", 32))
+        self.if_sr = bool(config.get("if_sr", False))
 
     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, text, output_file):
         request_params = {
@@ -51,4 +54,6 @@ class TTSProvider(TTSProviderBase):
             with open(output_file, "wb") as file:
                 file.write(resp.content)
         else:
-            logger.bind(tag=TAG).error(f"GPT_SoVITS_V3 TTS请求失败: {resp.status_code} - {resp.text}")
+            logger.bind(tag=TAG).error(
+                f"GPT_SoVITS_V3 TTS请求失败: {resp.status_code} - {resp.text}"
+            )

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

@@ -21,7 +21,7 @@ class TTSProvider(TTSProviderBase):
         else:
             self.voice = config.get("voice", "alloy")
         self.response_format = "wav"
-        self.speed = config.get("speed", 1.0)
+        self.speed = float(config.get("speed", 1.0))
         self.output_file = config.get("output_dir", "tmp/")
         check_model_key("TTS", self.api_key)
 

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

@@ -16,7 +16,7 @@ class TTSProvider(TTSProviderBase):
             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"))
         self.gain = config.get("gain")
 
         self.host = "api.siliconflow.cn"

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

@@ -19,7 +19,7 @@ class TTSProvider(TTSProviderBase):
         if config.get("private_voice"):
             self.voice = config.get("private_voice")
         else:
-            self.voice = config.get("voice")
+            self.voice = int(config.get("voice"))
         self.api_url = "https://tts.tencentcloudapi.com"  # 正确的API端点
         self.region = config.get("region")
         self.output_file = config.get("output_dir")

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

@@ -20,13 +20,13 @@ class TTSProvider(TTSProviderBase):
             self.voice_id = int(config.get("voice_id", 1695))
         self.token = config.get("token")
         self.to_lang = config.get("to_lang")
-        self.volume_change_dB = config.get("volume_change_dB", 0)
-        self.speed_factor = config.get("speed_factor", 1)
-        self.stream = config.get("stream", False)
+        self.volume_change_dB = int(config.get("volume_change_dB", 0))
+        self.speed_factor = int(config.get("speed_factor", 1))
+        self.stream = bool(config.get("stream", False))
         self.output_file = config.get("output_dir")
-        self.pitch_factor = config.get("pitch_factor", 0)
+        self.pitch_factor = int(config.get("pitch_factor", 0))
         self.format = config.get("format", "mp3")
-        self.emotion = config.get("emotion", 1)
+        self.emotion = int(config.get("emotion", 1))
         self.header = {"Content-Type": "application/json"}
 
     def generate_filename(self, extension=".mp3"):

main/xiaozhi-server/core/providers/vad/silero.py

@@ -21,8 +21,8 @@ class VADProvider(VADProviderBase):
         (get_speech_timestamps, _, _, _, _) = self.utils
 
         self.decoder = opuslib_next.Decoder(16000, 1)
-        self.vad_threshold = config.get("threshold")
-        self.silence_threshold_ms = config.get("min_silence_duration_ms")
+        self.vad_threshold = float(config.get("threshold", 0.5))
+        self.silence_threshold_ms = int(config.get("min_silence_duration_ms", 1000))
 
     def is_vad(self, conn, opus_packet):
         try: