update: 增加智能体独立音频设置

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

@@ -6,9 +6,9 @@ import queue
 import asyncio
 import traceback
 import websockets
+
 from asyncio import Task
 from config.logger import setup_logging
-from core.utils import opus_encoder_utils
 from core.utils.tts import MarkdownCleaner
 from core.providers.tts.base import TTSProviderBase
 from core.providers.tts.dto.dto import SentenceType, ContentType, InterfaceType
@@ -18,6 +18,12 @@ logger = setup_logging()
 
 
 class TTSProvider(TTSProviderBase):
+    TTS_PARAM_CONFIG = [
+        ("ttsVolume", "volume", 0, 100, 50, int),
+        ("ttsRate", "rate", 0.5, 2.0, 1.0, lambda v: round(v, 1)),
+        ("ttsPitch", "pitch", 0.5, 2.0, 1.0, lambda v: round(v, 1)),
+    ]
+
     def __init__(self, config, delete_audio_file):
         super().__init__(config, delete_audio_file)
 
@@ -51,6 +57,9 @@ class TTSProvider(TTSProviderBase):
         pitch = config.get("pitch", "1.0")
         self.pitch = float(pitch) if pitch 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.header = {
             "Authorization": f"Bearer {self.api_key}",
             # "user-agent": "your_platform_info", // 可选

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

@@ -1,15 +1,17 @@
 import uuid
 import json
 import hmac
+import time
 import hashlib
 import base64
 import requests
-from datetime import datetime
-from core.providers.tts.base import TTSProviderBase
-from config.logger import setup_logging
-import time
-import uuid
+
 from urllib import parse
+from datetime import datetime
+from config.logger import setup_logging
+from core.providers.tts.base import TTSProviderBase
+from core.utils.tts import convert_percentage_to_range
+
 
 TAG = __name__
 logger = setup_logging()
@@ -84,6 +86,11 @@ class AccessToken:
 
 
 class TTSProvider(TTSProviderBase):
+    TTS_PARAM_CONFIG = [
+        ("ttsVolume", "volume", 0, 100, 50, int),
+        ("ttsRate", "speech_rate", -500, 500, 0, int),
+        ("ttsPitch", "pitch_rate", -500, 500, 0, int),
+    ]
 
     def __init__(self, config, delete_audio_file):
         super().__init__(config, delete_audio_file)
@@ -110,6 +117,9 @@ class TTSProvider(TTSProviderBase):
         pitch_rate = config.get("pitch_rate", "0")
         self.pitch_rate = int(pitch_rate) if pitch_rate else 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.host = config.get("host", "nls-gateway-cn-shanghai.aliyuncs.com")
         self.api_url = f"https://{self.host}/stream/v1/tts"
         self.header = {"Content-Type": "application/json"}

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

@@ -1,4 +1,4 @@
-import random
+import os
 import uuid
 import json
 import hmac
@@ -8,16 +8,16 @@ import time
 import queue
 import asyncio
 import traceback
-from asyncio import Task
 import websockets
-import os
-from datetime import datetime
+
+from asyncio import Task
 from urllib import parse
+from datetime import datetime
+from config.logger import setup_logging
+from core.utils.tts import MarkdownCleaner
 from core.providers.tts.base import TTSProviderBase
 from core.providers.tts.dto.dto import SentenceType, ContentType, InterfaceType
-from core.utils.tts import MarkdownCleaner
-from core.utils import opus_encoder_utils, textUtils
-from config.logger import setup_logging
+
 
 TAG = __name__
 logger = setup_logging()
@@ -86,6 +86,12 @@ class AccessToken:
 
 
 class TTSProvider(TTSProviderBase):
+    TTS_PARAM_CONFIG = [
+        ("ttsVolume", "volume", 0, 100, 50, int),
+        ("ttsRate", "speech_rate", -500, 500, 0, int),
+        ("ttsPitch", "pitch_rate", -500, 500, 0, int),
+    ]
+
     def __init__(self, config, delete_audio_file):
         super().__init__(config, delete_audio_file)
 
@@ -115,6 +121,9 @@ class TTSProvider(TTSProviderBase):
         pitch_rate = config.get("pitch_rate", "0")
         self.pitch_rate = int(pitch_rate) if pitch_rate else 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)
+
         # WebSocket配置
         self.host = config.get("host", "nls-gateway-cn-beijing.aliyuncs.com")
         # 如果配置的是内网地址（包含-internal.aliyuncs.com），则使用ws协议，默认是wss协议

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

@@ -13,7 +13,7 @@ from typing import Callable, Any
 from abc import ABC, abstractmethod
 from config.logger import setup_logging
 from core.utils import opus_encoder_utils
-from core.utils.tts import MarkdownCleaner
+from core.utils.tts import MarkdownCleaner, convert_percentage_to_range
 from core.utils.output_counter import add_device_output
 from core.handle.reportHandle import enqueue_tts_report
 from core.handle.sendAudioHandle import sendAudioMessage
@@ -463,3 +463,10 @@ class TTSProviderBase(ABC):
                 self.processed_chars += len(full_text)
                 return True
         return False
+
+    def _apply_percentage_params(self, config):
+        """根据子类定义的 TTS_PARAM_CONFIG 批量应用百分比参数"""
+        for config_key, attr_name, min_val, max_val, base_val, transform in self.TTS_PARAM_CONFIG:
+            if config_key in config:
+                val = convert_percentage_to_range(config[config_key], min_val, max_val, base_val)
+                setattr(self, attr_name, transform(val) if transform else val)

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

@@ -2,15 +2,24 @@ import uuid
 import json
 import base64
 import requests
+
+from config.logger import setup_logging
 from core.utils.util import check_model_key
 from core.providers.tts.base import TTSProviderBase
-from config.logger import setup_logging
+from core.utils.tts import convert_percentage_to_range
+
 
 TAG = __name__
 logger = setup_logging()
 
 
 class TTSProvider(TTSProviderBase):
+    TTS_PARAM_CONFIG = [
+        ("ttsVolume", "volume_ratio", 0.1, 3, 1.0, lambda v: round(float(v), 1)),
+        ("ttsRate", "speed_ratio", 0.2, 3, 1.0, lambda v: round(float(v), 1)),
+        ("ttsPitch", "pitch_ratio", 0.1, 3, 1.0, lambda v: round(float(v), 1)),
+    ]
+
     def __init__(self, config, delete_audio_file):
         super().__init__(config, delete_audio_file)
         if config.get("appid"):
@@ -34,6 +43,9 @@ class TTSProvider(TTSProviderBase):
         self.volume_ratio = float(volume_ratio) if volume_ratio else 1.0
         self.pitch_ratio = float(pitch_ratio) if pitch_ratio 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.api_url = config.get("api_url")
         self.authorization = config.get("authorization")
         self.header = {"Authorization": f"{self.authorization}{self.access_token}"}

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

@@ -7,11 +7,10 @@ import traceback
 import websockets
 
 from typing import Callable, Any
-from core.utils.tts import MarkdownCleaner
 from config.logger import setup_logging
-from core.utils import opus_encoder_utils
 from core.utils.util import check_model_key
 from core.providers.tts.base import TTSProviderBase
+from core.utils.tts import MarkdownCleaner, convert_percentage_to_range
 from core.providers.tts.dto.dto import SentenceType, ContentType, InterfaceType
 
 
@@ -178,6 +177,22 @@ class TTSProvider(TTSProviderBase):
         self.additions = {**default_additions, **config.get("additions", {})}
         self.mix_speaker = {**default_mix_speaker, **config.get("mix_speaker", {})}
 
+        # 应用百分比调整（如果存在），否则使用公有化配置
+        if "ttsVolume" in config:
+            self.audio_params["loudness_rate"] = int(convert_percentage_to_range(
+                config["ttsVolume"], min_val=-50, max_val=100, base_val=0
+            ))
+
+        if "ttsRate" in config:
+            self.audio_params["speech_rate"] = int(convert_percentage_to_range(
+                config["ttsRate"], min_val=-50, max_val=100, base_val=0
+            ))
+
+        if "ttsPitch" in config:
+            self.additions["post_process"]["pitch"] = int(convert_percentage_to_range(
+                config["ttsPitch"], min_val=-12, max_val=12, base_val=0
+            ))
+
         self.ws_url = config.get("ws_url")
         self.authorization = config.get("authorization")
         self.header = {"Authorization": f"{self.authorization}{self.access_token}"}

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

@@ -6,12 +6,14 @@ import asyncio
 import aiohttp
 import requests
 import traceback
+
+from core.utils import textUtils
 from config.logger import setup_logging
-from core.utils.tts import MarkdownCleaner
 from core.utils.util import parse_string_to_list
 from core.providers.tts.base import TTSProviderBase
-from core.utils import opus_encoder_utils, textUtils
 from core.providers.tts.dto.dto import SentenceType, ContentType
+from core.utils.tts import MarkdownCleaner, convert_percentage_to_range
+
 
 TAG = __name__
 logger = setup_logging()
@@ -56,6 +58,22 @@ class TTSProvider(TTSProviderBase):
         if self.voice:
             self.voice_setting["voice_id"] = self.voice
 
+        # 应用百分比调整（如果存在），否则使用公有化配置
+        if "ttsVolume" in config:
+            self.voice_setting["vol"] = round(convert_percentage_to_range(
+                config["ttsVolume"], min_val=0.1, max_val=10, base_val=1.0
+            ), 1)
+
+        if "ttsRate" in config:
+            self.voice_setting["speed"] = round(convert_percentage_to_range(
+                config["ttsRate"], min_val=0.5, max_val=2, base_val=1.0
+            ), 1)
+
+        if "ttsPitch" in config:
+            self.voice_setting["pitch"] = int(convert_percentage_to_range(
+                config["ttsPitch"], min_val=-12, max_val=12, base_val=0
+            ))
+
         self.host = "api.minimaxi.com"  # 备用地址：api-bj.minimaxi.com
         self.api_url = f"https://{self.host}/v1/t2a_v2?GroupId={self.group_id}"
         self.header = {

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

@@ -16,6 +16,11 @@ logger = setup_logging()
 
 
 class TTSProvider(TTSProviderBase):
+    TTS_PARAM_CONFIG = [
+        ("ttsVolume", "volume", 0, 3, 1.0, lambda v: round(float(v), 1)),
+        ("ttsRate", "speed", 0, 3, 1.0, lambda v: round(float(v), 1)),
+    ]
+
     def __init__(self, config, delete_audio_file):
         super().__init__(config, delete_audio_file)
         self.url = config.get("url", "ws://192.168.1.10:8092/paddlespeech/tts/streaming")
@@ -33,6 +38,10 @@ class TTSProvider(TTSProviderBase):
         self.volume = float(volume) if volume else 1.0
         
         self.delete_audio_file = config.get("delete_audio", True)
+
+        # 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)
+
         if not self.delete_audio_file:
             timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
             save_path = config.get("save_path")

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

@@ -3,6 +3,11 @@ from core.providers.tts.base import TTSProviderBase
 
 
 class TTSProvider(TTSProviderBase):
+    TTS_PARAM_CONFIG = [
+        ("ttsVolume", "gain", -10, 10, 0, int),
+        ("ttsRate", "speed", 0.25, 4, 1, lambda v: round(float(v), 1)),
+    ]
+
     def __init__(self, config, delete_audio_file):
         super().__init__(config, delete_audio_file)
         self.model = config.get("model")
@@ -16,6 +21,9 @@ class TTSProvider(TTSProviderBase):
         self.speed = float(config.get("speed", 1.0))
         self.gain = config.get("gain")
 
+        # 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.host = "api.siliconflow.cn"
         self.api_url = f"https://{self.host}/v1/audio/speech"
 

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

@@ -12,6 +12,12 @@ logger = setup_logging()
 
 
 class TTSProvider(TTSProviderBase):
+    TTS_PARAM_CONFIG = [
+        ("ttsVolume", "volume_change_dB", -10, 10, 0, int),
+        ("ttsRate", "speed_factor", 0.5, 2, 0, lambda v: round(float(v), 1)),
+        ("ttsPitch", "pitch_factor", -8, 8, 0, lambda v: round(float(v), 1)),
+    ]
+
     def __init__(self, config, delete_audio_file):
         super().__init__(config, delete_audio_file)
         self.url = config.get(
@@ -34,6 +40,9 @@ class TTSProvider(TTSProviderBase):
         self.emotion = int(config.get("emotion", 1))
         self.header = {"Content-Type": "application/json"}
 
+        # 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)
+
     def generate_filename(self, extension=".mp3"):
         return os.path.join(
             self.output_file,

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

@@ -9,9 +9,9 @@ import hashlib
 import asyncio
 import traceback
 import websockets
+
 from asyncio import Task
 from config.logger import setup_logging
-from core.utils import opus_encoder_utils
 from core.utils.tts import MarkdownCleaner
 from urllib.parse import urlencode, urlparse
 from core.providers.tts.base import TTSProviderBase
@@ -59,6 +59,12 @@ class XunfeiWSAuth:
 
 
 class TTSProvider(TTSProviderBase):
+    TTS_PARAM_CONFIG = [
+        ("ttsVolume", "volume", 0, 100, 50, int),
+        ("ttsRate", "speed", 0, 100, 50, int),
+        ("ttsPitch", "pitch", 0, 100, 50, int),
+    ]
+
     def __init__(self, config, delete_audio_file):
         super().__init__(config, delete_audio_file)
 
@@ -88,6 +94,9 @@ class TTSProvider(TTSProviderBase):
         pitch = config.get("pitch", "50")
         self.pitch = int(pitch) if pitch else 50
 
+        # 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)
+
         # 音频编码配置
         self.format = config.get("format", "raw")
 

main/xiaozhi-server/core/utils/tts.py

@@ -141,4 +141,31 @@ class MarkdownCleaner:
         # 去除emoji表情
         text = check_emoji(text)
 
-        return text.strip()
+        return text.strip()
+
+def convert_percentage_to_range(percentage, min_val, max_val, base_val=None):
+    """
+    将百分比(-100~100)转换为指定范围的值
+
+    Args:
+        percentage: 百分比值 (-100 到 100)
+        min_val: 目标范围最小值
+        max_val: 目标范围最大值
+        base_val: 基准值（可选，默认为范围中点）
+
+    Returns:
+        转换后的值
+    """
+    if base_val is None:
+        base_val = (min_val + max_val) / 2
+
+    # 百分比 -100 对应 min_val, 0 对应 base_val, 100 对应 max_val
+    if percentage < 0:
+        # 负百分比：从 base_val 向 min_val 线性插值
+        result = base_val + (base_val - min_val) * (percentage / 100)
+    else:
+        # 正百分比：从 base_val 向 max_val 线性插值
+        result = base_val + (max_val - base_val) * (percentage / 100)
+
+    # 确保结果在有效范围内
+    return max(min_val, min(max_val, result))