Merge pull request #2016 from xinnan-tech/py_huoshanTTS_AddConfig

update: huoshanTTS add config

main/manager-api/src/main/java/xiaozhi/common/constant/Constant.java

@@ -237,7 +237,7 @@ public interface Constant {
     /**
      * 版本号
      */
-    public static final String VERSION = "0.7.3";
+    public static final String VERSION = "0.7.4";
 
     /**
      * 无效固件URL

main/manager-api/src/main/resources/db/changelog/202508111734.sql

@@ -0,0 +1,16 @@
+-- 更新HuoshanDoubleStreamTTS供应器增加语速，音调等配置
+UPDATE `ai_model_provider`
+SET fields = '[{"key": "ws_url", "type": "string", "label": "WebSocket地址"}, {"key": "appid", "type": "string", "label": "应用ID"}, {"key": "access_token", "type": "string", "label": "访问令牌"}, {"key": "resource_id", "type": "string", "label": "资源ID"}, {"key": "speaker", "type": "string", "label": "默认音色"}, {"key": "speech_rate", "type": "number", "label": "语速(-50~100)"}, {"key": "loudness_rate", "type": "number", "label": "音量(-50~100)"}, {"key": "pitch", "type": "number", "label": "音高(-12~12)"}]'
+WHERE id = 'SYSTEM_TTS_HSDSTTS';
+
+UPDATE `ai_model_config` SET 
+`doc_link` = 'https://console.volcengine.com/speech/service/10007',
+`remark` = '火山引擎语音合成服务配置说明：
+1. 访问 https://www.volcengine.com/ 注册并开通火山引擎账号
+2. 访问 https://console.volcengine.com/speech/service/10007 开通语音合成大模型，购买音色
+3. 在页面底部获取appid和access_token
+5. 资源ID固定为：volc.service_type.10029（大模型语音合成及混音）
+6. 语速：-50~100，可不填，正常默认值0，可填-50~100
+7. 音量：-50~100，可不填，正常默认值0，可填-50~100
+8. 音高：-12~12，可不填，正常默认值0，可填-12~12
+9. 填入配置文件中' WHERE `id` = 'TTS_HuoshanDoubleStreamTTS';

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

@@ -289,3 +289,10 @@ databaseChangeLog:
         - sqlFile:
             encoding: utf8
             path: classpath:db/changelog/202508081701.sql
+  - changeSet:
+      id: 202508111734
+      author: RanChen
+      changes:
+        - sqlFile:
+            encoding: utf8
+            path: classpath:db/changelog/202508111734.sql

main/xiaozhi-server/config.yaml

@@ -586,6 +586,9 @@ TTS:
     access_token: 你的火山引擎语音合成服务access_token
     resource_id: volc.service_type.10029
     speaker: zh_female_wanwanxiaohe_moon_bigtts
+    speech_rate: 0
+    loudness_rate: 0
+    pitch: 0
   CosyVoiceSiliconflow:
     type: siliconflow
     # 硅基流动TTS

main/xiaozhi-server/config/logger.py

@@ -5,7 +5,7 @@ from config.config_loader import load_config
 from config.settings import check_config_file
 from datetime import datetime
 
-SERVER_VERSION = "0.7.3"
+SERVER_VERSION = "0.7.4"
 _logger_initialized = False
 
 

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

@@ -152,6 +152,12 @@ class TTSProvider(TTSProviderBase):
             self.voice = config.get("private_voice")
         else:
             self.voice = config.get("speaker")
+        speech_rate = config.get("speech_rate", "0")
+        loudness_rate = config.get("loudness_rate", "0")
+        pitch = config.get("pitch", "0")
+        self.speech_rate = int(speech_rate) if speech_rate else 0
+        self.loudness_rate = int(loudness_rate) if loudness_rate else 0
+        self.pitch = int(pitch) if pitch else 0
         self.ws_url = config.get("ws_url")
         self.authorization = config.get("authorization")
         self.header = {"Authorization": f"{self.authorization}{self.access_token}"}
@@ -636,8 +642,15 @@ class TTSProvider(TTSProviderBase):
                         "audio_params": {
                             "format": audio_format,
                             "sample_rate": audio_sample_rate,
+                            "speech_rate": self.speech_rate,
+                            "loudness_rate": self.loudness_rate
                         },
                     },
+                    "additions": {
+                        "post_process": {
+                            "pitch": self.pitch
+                        }
+                    }
                 }
             )
         )