Merge pull request #3238 from xinnan-tech/py-add-edge-config

补充edge相关配置

main/manager-api/src/main/resources/db/changelog/202606231030.sql

@@ -0,0 +1,15 @@
+-- 更新EdgeTTS供应器增加语速、音调、音量配置
+UPDATE `ai_model_provider`
+SET fields = '[{"key":"voice","label":"音色","type":"string"},{"key":"output_dir","label":"输出目录","type":"string"},{"key":"rate","label":"语速(-100~100)","type":"number"},{"key":"volume","label":"音量(0~100)","type":"number"},{"key":"pitch","label":"音调(-100~100)","type":"number"}]'
+WHERE id = 'SYSTEM_TTS_edge';
+
+UPDATE `ai_model_config` SET
+`remark` = 'EdgeTTS配置说明：
+1. 使用微软Edge TTS服务
+2. 支持多种语言和音色
+3. 免费使用，无需注册
+4. 需要网络连接
+5. 输出文件保存在tmp/目录
+6. 语速：-100~100，0为正常速度
+7. 音量：0~100，50为正常音量
+8. 音调：-100~100，0为正常音调' WHERE `id` = 'TTS_EdgeTTS';

main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml

@@ -676,3 +676,10 @@ databaseChangeLog:
         - sqlFile:
             encoding: utf8
             path: classpath:db/changelog/202605251426.sql
+  - changeSet:
+      id: 202606231030
+      author: RanChen
+      changes:
+        - sqlFile:
+            encoding: utf8
+            path: classpath:db/changelog/202606231030.sql

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

@@ -6,6 +6,12 @@ from core.providers.tts.base import TTSProviderBase
 
 
 class TTSProvider(TTSProviderBase):
+    TTS_PARAM_CONFIG = [
+        ("ttsVolume", "volume", 0, 100, 50, int),
+        ("ttsRate", "speech_rate", -100, 100, 0, int),
+        ("ttsPitch", "pitch_rate", -100, 100, 0, int),
+    ]
+
     def __init__(self, config, delete_audio_file):
         super().__init__(config, delete_audio_file)
         if config.get("private_voice"):
@@ -14,6 +20,22 @@ class TTSProvider(TTSProviderBase):
             self.voice = config.get("voice")
         self.audio_file_type = config.get("format", "mp3")
 
+        volume = config.get("volume", "50")
+        self.volume = int(volume) if volume else 50
+
+        speech_rate = config.get("rate", "0")
+        self.speech_rate = int(speech_rate) if speech_rate else 0
+
+        pitch_rate = config.get("pitch", "0")
+        self.pitch_rate = int(pitch_rate) if pitch_rate else 0
+
+        # 应用百分比调整
+        self._apply_percentage_params(config)
+
+        self.edge_rate = f"{self.speech_rate:+}%"
+        self.edge_volume = f"{self.volume:+}%"
+        self.edge_pitch = f"{self.pitch_rate:+}Hz"
+
     def generate_filename(self, extension=".mp3"):
         return os.path.join(
             self.output_file,
@@ -22,7 +44,13 @@ class TTSProvider(TTSProviderBase):
 
     async def text_to_speak(self, text, output_file):
         try:
-            communicate = edge_tts.Communicate(text, voice=self.voice)
+            communicate = edge_tts.Communicate(
+                text,
+                voice=self.voice,
+                rate=self.edge_rate,
+                volume=self.edge_volume,
+                pitch=self.edge_pitch,
+            )
             if output_file:
                 # 确保目录存在并创建空文件
                 os.makedirs(os.path.dirname(output_file), exist_ok=True)