update: 增加智能体独立音频设置

main/manager-api/src/main/java/xiaozhi/modules/agent/dto/AgentUpdateDTO.java

@@ -1,6 +1,7 @@
 package xiaozhi.modules.agent.dto;
 
 import java.io.Serializable;
+import java.math.BigDecimal;
 import java.util.HashMap;
 import java.util.List;
 
@@ -44,6 +45,15 @@ public class AgentUpdateDTO implements Serializable {
     @Schema(description = "音色语言", example = "普通话", nullable = true)
     private String ttsLanguage;
 
+    @Schema(description = "TTS音量", example = "50", nullable = true)
+    private Integer ttsVolume;
+
+    @Schema(description = "TTS语速", example = "50", nullable = true)
+    private Integer ttsRate;
+
+    @Schema(description = "TTS音调", example = "50", nullable = true)
+    private Integer ttsPitch;
+
     @Schema(description = "记忆模型标识", example = "mem_model_02", nullable = true)
     private String memModelId;
 

main/manager-api/src/main/java/xiaozhi/modules/agent/entity/AgentEntity.java

@@ -1,5 +1,6 @@
 package xiaozhi.modules.agent.entity;
 
+import java.math.BigDecimal;
 import java.util.Date;
 
 import com.baomidou.mybatisplus.annotation.IdType;
@@ -48,6 +49,15 @@ public class AgentEntity {
     @Schema(description = "音色语言")
     private String ttsLanguage;
 
+    @Schema(description = "TTS音量")
+    private Integer ttsVolume;
+
+    @Schema(description = "TTS语速")
+    private Integer ttsRate;
+
+    @Schema(description = "TTS音调")
+    private Integer ttsPitch;
+
     @Schema(description = "记忆模型标识")
     private String memModelId;
 

main/manager-api/src/main/java/xiaozhi/modules/agent/entity/AgentTemplateEntity.java

@@ -1,6 +1,7 @@
 package xiaozhi.modules.agent.entity;
 
 import java.io.Serializable;
+import java.math.BigDecimal;
 import java.util.Date;
 
 import com.baomidou.mybatisplus.annotation.IdType;
@@ -69,6 +70,21 @@ public class AgentTemplateEntity implements Serializable {
      */
     private String ttsLanguage;
 
+    /**
+     * TTS音量
+     */
+    private Integer ttsVolume;
+
+    /**
+     * TTS语速
+     */
+    private Integer ttsRate;
+
+    /**
+     * TTS音调
+     */
+    private Integer ttsPitch;
+
     /**
      * 记忆模型标识
      */

main/manager-api/src/main/java/xiaozhi/modules/agent/service/impl/AgentServiceImpl.java

@@ -285,6 +285,15 @@ public class AgentServiceImpl extends BaseServiceImpl<AgentDao, AgentEntity> imp
         if (dto.getTtsLanguage() != null) {
             existingEntity.setTtsLanguage(dto.getTtsLanguage());
         }
+        if (dto.getTtsVolume() != null) {
+            existingEntity.setTtsVolume(dto.getTtsVolume());
+        }
+        if (dto.getTtsRate() != null) {
+            existingEntity.setTtsRate(dto.getTtsRate());
+        }
+        if (dto.getTtsPitch() != null) {
+            existingEntity.setTtsPitch(dto.getTtsPitch());
+        }
         if (dto.getMemModelId() != null) {
             existingEntity.setMemModelId(dto.getMemModelId());
         }

main/manager-api/src/main/java/xiaozhi/modules/config/service/impl/ConfigServiceImpl.java

@@ -88,6 +88,9 @@ public class ConfigServiceImpl implements ConfigService {
                 null,
                 null,
                 null,
+                null,
+                null,
+                null,
                 agent.getVadModelId(),
                 agent.getAsrModelId(),
                 null,
@@ -219,6 +222,9 @@ public class ConfigServiceImpl implements ConfigService {
                 referenceAudio,
                 referenceText,
                 language,
+                agent.getTtsVolume(),
+                agent.getTtsRate(),
+                agent.getTtsPitch(),
                 agent.getVadModelId(),
                 agent.getAsrModelId(),
                 agent.getLlmModelId(),
@@ -397,6 +403,9 @@ public class ConfigServiceImpl implements ConfigService {
             String referenceAudio,
             String referenceText,
             String language,
+            Integer ttsVolume,
+            Integer ttsRate,
+            Integer ttsPitch,
             String vadModelId,
             String asrModelId,
             String llmModelId,
@@ -437,6 +446,12 @@ public class ConfigServiceImpl implements ConfigService {
                         ((Map<String, Object>) model.getConfigJson()).put("ref_text", referenceText);
                     if (language != null)
                         ((Map<String, Object>) model.getConfigJson()).put("language", language);
+                    if (ttsVolume != null)
+                        ((Map<String, Object>) model.getConfigJson()).put("ttsVolume", ttsVolume);
+                    if (ttsRate != null)
+                        ((Map<String, Object>) model.getConfigJson()).put("ttsRate", ttsRate);
+                    if (ttsPitch != null)
+                        ((Map<String, Object>) model.getConfigJson()).put("ttsPitch", ttsPitch);
 
                     // 火山引擎声音克隆需要替换resource_id
                     Map<String, Object> map = (Map<String, Object>) model.getConfigJson();

main/manager-api/src/main/resources/db/changelog/202602061650.sql

@@ -13,8 +13,36 @@ SET languages = CASE
     ELSE languages
 END;
 
--- 添加音色语言字段到 ai_agent 表
+-- 添加音色语言、音量、语速、音调字段到 ai_agent 表
-ALTER TABLE `ai_agent` ADD COLUMN `tts_language` VARCHAR(50) NULL COMMENT '音色语言' AFTER `tts_voice_id`;
+SET @col_exists = (SELECT COUNT(*) FROM INFORMATION_SCHEMA.COLUMNS WHERE TABLE_SCHEMA = DATABASE() AND TABLE_NAME = 'ai_agent' AND COLUMN_NAME = 'tts_language');
+SET @sql = IF(@col_exists = 0, 'ALTER TABLE `ai_agent` ADD COLUMN `tts_language` VARCHAR(50) NULL COMMENT ''音色语言'' AFTER `tts_voice_id`', 'SELECT ''Column tts_language already exists'' AS msg');
+PREPARE stmt FROM @sql; EXECUTE stmt; DEALLOCATE PREPARE stmt;
 
--- 添加音色语言字段到 ai_agent_template 表
+SET @col_exists = (SELECT COUNT(*) FROM INFORMATION_SCHEMA.COLUMNS WHERE TABLE_SCHEMA = DATABASE() AND TABLE_NAME = 'ai_agent' AND COLUMN_NAME = 'tts_volume');
-ALTER TABLE `ai_agent_template` ADD COLUMN `tts_language` VARCHAR(50) NULL COMMENT '音色语言' AFTER `tts_voice_id`;
+SET @sql = IF(@col_exists = 0, 'ALTER TABLE `ai_agent` ADD COLUMN `tts_volume` INT NULL COMMENT ''TTS音量'' AFTER `tts_language`', 'SELECT ''Column tts_volume already exists'' AS msg');
+PREPARE stmt FROM @sql; EXECUTE stmt; DEALLOCATE PREPARE stmt;
+
+SET @col_exists = (SELECT COUNT(*) FROM INFORMATION_SCHEMA.COLUMNS WHERE TABLE_SCHEMA = DATABASE() AND TABLE_NAME = 'ai_agent' AND COLUMN_NAME = 'tts_rate');
+SET @sql = IF(@col_exists = 0, 'ALTER TABLE `ai_agent` ADD COLUMN `tts_rate` INT NULL COMMENT ''TTS语速'' AFTER `tts_volume`', 'SELECT ''Column tts_rate already exists'' AS msg');
+PREPARE stmt FROM @sql; EXECUTE stmt; DEALLOCATE PREPARE stmt;
+
+SET @col_exists = (SELECT COUNT(*) FROM INFORMATION_SCHEMA.COLUMNS WHERE TABLE_SCHEMA = DATABASE() AND TABLE_NAME = 'ai_agent' AND COLUMN_NAME = 'tts_pitch');
+SET @sql = IF(@col_exists = 0, 'ALTER TABLE `ai_agent` ADD COLUMN `tts_pitch` INT NULL COMMENT ''TTS音调'' AFTER `tts_rate`', 'SELECT ''Column tts_pitch already exists'' AS msg');
+PREPARE stmt FROM @sql; EXECUTE stmt; DEALLOCATE PREPARE stmt;
+
+-- 添加音色语言、音量、语速、音调字段到 ai_agent_template 表
+SET @col_exists = (SELECT COUNT(*) FROM INFORMATION_SCHEMA.COLUMNS WHERE TABLE_SCHEMA = DATABASE() AND TABLE_NAME = 'ai_agent_template' AND COLUMN_NAME = 'tts_language');
+SET @sql = IF(@col_exists = 0, 'ALTER TABLE `ai_agent_template` ADD COLUMN `tts_language` VARCHAR(50) NULL COMMENT ''音色语言'' AFTER `tts_voice_id`', 'SELECT ''Column tts_language already exists'' AS msg');
+PREPARE stmt FROM @sql; EXECUTE stmt; DEALLOCATE PREPARE stmt;
+
+SET @col_exists = (SELECT COUNT(*) FROM INFORMATION_SCHEMA.COLUMNS WHERE TABLE_SCHEMA = DATABASE() AND TABLE_NAME = 'ai_agent_template' AND COLUMN_NAME = 'tts_volume');
+SET @sql = IF(@col_exists = 0, 'ALTER TABLE `ai_agent_template` ADD COLUMN `tts_volume` INT NULL COMMENT ''TTS音量'' AFTER `tts_language`', 'SELECT ''Column tts_volume already exists'' AS msg');
+PREPARE stmt FROM @sql; EXECUTE stmt; DEALLOCATE PREPARE stmt;
+
+SET @col_exists = (SELECT COUNT(*) FROM INFORMATION_SCHEMA.COLUMNS WHERE TABLE_SCHEMA = DATABASE() AND TABLE_NAME = 'ai_agent_template' AND COLUMN_NAME = 'tts_rate');
+SET @sql = IF(@col_exists = 0, 'ALTER TABLE `ai_agent_template` ADD COLUMN `tts_rate` INT NULL COMMENT ''TTS语速'' AFTER `tts_volume`', 'SELECT ''Column tts_rate already exists'' AS msg');
+PREPARE stmt FROM @sql; EXECUTE stmt; DEALLOCATE PREPARE stmt;
+
+SET @col_exists = (SELECT COUNT(*) FROM INFORMATION_SCHEMA.COLUMNS WHERE TABLE_SCHEMA = DATABASE() AND TABLE_NAME = 'ai_agent_template' AND COLUMN_NAME = 'tts_pitch');
+SET @sql = IF(@col_exists = 0, 'ALTER TABLE `ai_agent_template` ADD COLUMN `tts_pitch` INT NULL COMMENT ''TTS音调'' AFTER `tts_rate`', 'SELECT ''Column tts_pitch already exists'' AS msg');
+PREPARE stmt FROM @sql; EXECUTE stmt; DEALLOCATE PREPARE stmt;

main/manager-api/src/main/resources/mapper/agent/AgentDao.xml

@@ -17,6 +17,9 @@
         <result column="ttsModelId" property="ttsModelId"/>
         <result column="ttsVoiceId" property="ttsVoiceId"/>
         <result column="ttsLanguage" property="ttsLanguage"/>
+        <result column="ttsVolume" property="ttsVolume"/>
+        <result column="ttsRate" property="ttsRate"/>
+        <result column="ttsPitch" property="ttsPitch"/>
         <result column="memModelId" property="memModelId"/>
         <result column="intentModelId" property="intentModelId"/>
 
@@ -47,6 +50,9 @@
                a.tts_model_id      AS ttsModelId,
                a.tts_voice_id      AS ttsVoiceId,
                a.tts_language      AS ttsLanguage,
+               a.tts_volume        AS ttsVolume,
+               a.tts_rate          AS ttsRate,
+               a.tts_pitch         AS ttsPitch,
                a.mem_model_id      AS memModelId,
                a.intent_model_id   AS intentModelId,
                COALESCE(

main/manager-web/src/components/TtsAdvancedSettings.vue

@@ -0,0 +1,240 @@
+<template>
+  <el-drawer
+    :visible.sync="drawerVisible"
+    :before-close="handleClose"
+    direction="rtl"
+    size="400px"
+    :modal="true"
+    :show-close="false"
+    custom-class="tts-advanced-drawer"
+  >
+    <div class="drawer-header" slot="title">
+      <span class="drawer-title">{{ $t('roleConfig.advancedSettings') }}</span>
+      <button class="drawer-close-btn" @click="handleClose">×</button>
+    </div>
+
+    <div class="drawer-content">
+      <el-form label-position="top">
+        <!-- 音量 -->
+        <el-form-item :label="$t('roleConfig.ttsVolume')">
+          <div class="slider-container">
+            <el-slider
+              v-model="localSettings.volume"
+              :min="-100"
+              :max="100"
+              :step="1"
+              :format-tooltip="formatTooltip"
+              class="tts-slider"
+            />
+            <span class="slider-hint">{{ $t('roleConfig.volumeHint') }}</span>
+          </div>
+        </el-form-item>
+
+        <!-- 语速 -->
+        <el-form-item :label="$t('roleConfig.ttsRate')">
+          <div class="slider-container">
+            <el-slider
+              v-model="localSettings.speed"
+              :min="-100"
+              :max="100"
+              :step="1"
+              :format-tooltip="formatTooltip"
+              class="tts-slider"
+            />
+            <span class="slider-hint">{{ $t('roleConfig.speedHint') }}</span>
+          </div>
+        </el-form-item>
+
+        <!-- 音调 -->
+        <el-form-item :label="$t('roleConfig.ttsPitch')">
+          <div class="slider-container">
+            <el-slider
+              v-model="localSettings.pitch"
+              :min="-100"
+              :max="100"
+              :step="1"
+              :format-tooltip="formatTooltip"
+              class="tts-slider"
+            />
+            <span class="slider-hint">{{ $t('roleConfig.pitchHint') }}</span>
+          </div>
+        </el-form-item>
+      </el-form>
+    </div>
+
+    <div class="drawer-footer">
+      <el-button @click="handleCancel">{{ $t('button.cancel') }}</el-button>
+      <el-button type="primary" @click="handleSave">{{ $t('button.save') }}</el-button>
+    </div>
+  </el-drawer>
+</template>
+
+<script>
+export default {
+  name: 'TtsAdvancedSettings',
+  props: {
+    visible: {
+      type: Boolean,
+      default: false
+    },
+    settings: {
+      type: Object,
+      default: () => ({
+        volume: 0,
+        speed: 0,
+        pitch: 0
+      })
+    }
+  },
+  data() {
+    return {
+      localSettings: {
+        volume: 0,
+        speed: 0,
+        pitch: 0
+      }
+    };
+  },
+  computed: {
+    drawerVisible: {
+      get() {
+        return this.visible;
+      },
+      set(val) {
+        this.$emit('update:visible', val);
+      }
+    }
+  },
+  watch: {
+    visible(newVal) {
+      if (newVal) {
+        // 当抽屉打开时，复制当前设置到本地
+        this.localSettings = { ...this.settings };
+      }
+    }
+  },
+  methods: {
+    handleClose() {
+      this.$emit('update:visible', false);
+    },
+    handleCancel() {
+      // 取消时不保存，直接关闭
+      this.handleClose();
+    },
+    handleSave() {
+      // 保存设置并关闭
+      this.$emit('save', { ...this.localSettings });
+      this.handleClose();
+    },
+    formatTooltip(val) {
+      return `${val}%`;
+    }
+  }
+};
+</script>
+
+<style scoped>
+.drawer-header {
+  display: flex;
+  align-items: center;
+  justify-content: space-between;
+  padding: 20px 24px;
+  border-bottom: 1px solid #e8f0ff;
+}
+
+.drawer-title {
+  font-size: 18px;
+  font-weight: 600;
+  color: #3d4566;
+}
+
+.drawer-close-btn {
+  width: 32px;
+  height: 32px;
+  border-radius: 50%;
+  border: 2px solid #cfcfcf;
+  background: none;
+  font-size: 28px;
+  font-weight: lighter;
+  color: #cfcfcf;
+  cursor: pointer;
+  display: flex;
+  align-items: center;
+  justify-content: center;
+  padding: 0;
+  outline: none;
+  transition: all 0.3s;
+}
+
+.drawer-close-btn:hover {
+  color: #409eff;
+  border-color: #409eff;
+}
+
+.drawer-content {
+  padding: 24px;
+  flex: 1;
+  overflow-y: auto;
+}
+
+.slider-container {
+  width: 100%;
+}
+
+.slider-hint {
+  display: block;
+  font-size: 12px;
+  color: #909399;
+  margin-top: 8px;
+  line-height: 1.5;
+}
+
+.tts-slider {
+  width: 100%;
+}
+
+.tts-slider ::v-deep .el-slider__input {
+  width: 80px;
+}
+
+.tts-slider ::v-deep .el-input__inner {
+  text-align: center;
+  padding: 0 8px;
+}
+
+.drawer-footer {
+  padding: 16px 24px;
+  border-top: 1px solid #e8f0ff;
+  display: flex;
+  justify-content: center;
+  gap: 12px;
+}
+
+.drawer-footer .el-button {
+  min-width: 80px;
+}
+
+::v-deep .el-form-item__label {
+  font-size: 14px !important;
+  color: #3d4566 !important;
+  font-weight: 500;
+  padding-bottom: 8px;
+}
+
+::v-deep .el-form-item {
+  margin-bottom: 24px;
+}
+</style>
+
+<style>
+.tts-advanced-drawer .el-drawer__header {
+  margin-bottom: 0;
+  padding: 0;
+}
+
+.tts-advanced-drawer .el-drawer__body {
+  display: flex;
+  flex-direction: column;
+  padding: 0;
+}
+</style>

main/manager-web/src/i18n/de.js

@@ -764,6 +764,14 @@ export default {
   'roleConfig.intent': 'Intent',
   'roleConfig.language': 'Sprache auswählen',
   'roleConfig.voiceType': 'Stimmtyp',
+  'roleConfig.ttsVolume': 'Lautstärke',
+  'roleConfig.ttsRate': 'Geschwindigkeit',
+  'roleConfig.ttsPitch': 'Tonhöhe',
+  'roleConfig.ttsAdvanced': 'TTS-Parameter',
+  'roleConfig.advancedSettings': 'Erweiterte Einstellungen',
+  'roleConfig.volumeHint': '-100=Min, 0=Standard, 100=Max',
+  'roleConfig.speedHint': '-100=Langsamste, 0=Standard, 100=Schnellste',
+  'roleConfig.pitchHint': '-100=Niedrigste, 0=Standard, 100=Höchste',
   'roleConfig.pleaseEnterContent': 'Bitte Inhalt eingeben',
   'roleConfig.pleaseEnterLangCode': 'Bitte Sprachcode eingeben, z.B.: en_US',
   'roleConfig.pleaseEnterLangName': 'Bitte Interaktionssprache eingeben, z.B.: Englisch',

main/manager-web/src/i18n/en.js

@@ -764,6 +764,14 @@ export default {
   'roleConfig.intent': 'Intent Recognition',
   'roleConfig.language': 'Select Language',
   'roleConfig.voiceType': 'Voice Type',
+  'roleConfig.ttsVolume': 'Volume',
+  'roleConfig.ttsRate': 'Speed',
+  'roleConfig.ttsPitch': 'Pitch',
+  'roleConfig.ttsAdvanced': 'TTS Parameters',
+  'roleConfig.advancedSettings': 'Advanced Settings',
+  'roleConfig.volumeHint': '-100=Min, 0=Standard, 100=Max',
+  'roleConfig.speedHint': '-100=Slowest, 0=Standard, 100=Fastest',
+  'roleConfig.pitchHint': '-100=Lowest, 0=Standard, 100=Highest',
   'roleConfig.pleaseEnterContent': 'Please enter content',
   'roleConfig.pleaseEnterLangCode': 'Please enter language code, e.g.: en_US',
   'roleConfig.pleaseEnterLangName': 'Please enter interaction language, e.g.: English',

main/manager-web/src/i18n/vi.js

@@ -764,6 +764,14 @@ export default {
   'roleConfig.intent': 'Nhận dạng ý định',
   'roleConfig.language': 'Chọn ngôn ngữ',
   'roleConfig.voiceType': 'Loại giọng nói',
+  'roleConfig.ttsVolume': 'Âm lượng',
+  'roleConfig.ttsRate': 'Tốc độ',
+  'roleConfig.ttsPitch': 'Cao độ',
+  'roleConfig.ttsAdvanced': 'Tham số TTS',
+  'roleConfig.advancedSettings': 'Cài đặt nâng cao',
+  'roleConfig.volumeHint': '-100=Tối thiểu, 0=Tiêu chuẩn, 100=Tối đa',
+  'roleConfig.speedHint': '-100=Chậm nhất, 0=Tiêu chuẩn, 100=Nhanh nhất',
+  'roleConfig.pitchHint': '-100=Thấp nhất, 0=Tiêu chuẩn, 100=Cao nhất',
   'roleConfig.pleaseEnterContent': 'Vui lòng nhập nội dung',
   'roleConfig.pleaseEnterLangCode': 'Vui lòng nhập mã ngôn ngữ, ví dụ: en_US',
   'roleConfig.pleaseEnterLangName': 'Vui lòng nhập ngôn ngữ tương tác, ví dụ: Tiếng Anh',

main/manager-web/src/i18n/zh_CN.js

@@ -764,6 +764,14 @@ export default {
   'roleConfig.tts': '语音合成(TTS)',
   'roleConfig.language': '选择语言',
   'roleConfig.voiceType': '声音音色(Voice)',
+  'roleConfig.ttsVolume': '音量',
+  'roleConfig.ttsRate': '语速',
+  'roleConfig.ttsPitch': '音调',
+  'roleConfig.ttsAdvanced': 'TTS参数',
+  'roleConfig.advancedSettings': '高级设置',
+  'roleConfig.volumeHint': '-100=最小, 0=标准, 100=最大',
+  'roleConfig.speedHint': '-100=最慢, 0=标准, 100=最快',
+  'roleConfig.pitchHint': '-100=最低, 0=标准, 100=最高',
   'roleConfig.pleaseEnterContent': '请输入内容',
   'roleConfig.pleaseEnterLangCode': '请输入语言编码，如：zh_CN',
   'roleConfig.pleaseEnterLangName': '请输入交互语种，如：中文',

main/manager-web/src/i18n/zh_TW.js

@@ -764,6 +764,14 @@ export default {
   'roleConfig.intent': '意圖識別(Intent)',
   'roleConfig.language': '選擇語言',
   'roleConfig.voiceType': '聲音音色(Voice)',
+  'roleConfig.ttsVolume': '音量',
+  'roleConfig.ttsRate': '語速',
+  'roleConfig.ttsPitch': '音調',
+  'roleConfig.ttsAdvanced': 'TTS參數',
+  'roleConfig.advancedSettings': '高級設置',
+  'roleConfig.volumeHint': '-100=最小, 0=標準, 100=最大',
+  'roleConfig.speedHint': '-100=最慢, 0=標準, 100=最快',
+  'roleConfig.pitchHint': '-100=最低, 0=標準, 100=最高',
   'roleConfig.pleaseEnterContent': '請輸入內容',
   'roleConfig.pleaseEnterLangCode': '請輸入語言編碼，如：zh_TW',
   'roleConfig.pleaseEnterLangName': '請輸入交互語種，如：繁體中文',

main/manager-web/src/views/roleConfig.vue

@@ -234,12 +234,12 @@
                     </el-form-item>
                     <div class="model-row">
                       <!-- 语言筛选器 -->
-                      <el-form-item :label="$t('roleConfig.language')" class="model-item">
+                      <el-form-item :label="$t('roleConfig.language')" class="model-item language-select-item">
                         <div class="model-select-wrapper">
                           <el-select
                             v-model="selectedLanguage"
                             :placeholder="$t('roleConfig.selectLanguage')"
-                            class="form-select"
+                            class="form-select language-select"
                             @change="filterVoicesByLanguage"
                           >
                             <el-option
@@ -251,7 +251,7 @@
                           </el-select>
                         </div>
                       </el-form-item>
-                      
+
                       <!-- 音色选择器 -->
                       <el-form-item :label="$t('roleConfig.voiceType')" class="model-item">
                         <div class="model-select-wrapper">
@@ -294,6 +294,13 @@
                               </div>
                             </el-option>
                           </el-select>
+                          <el-button
+                            class="edit-function-btn"
+                            style="margin-left: 10px;"
+                            @click="openTtsAdvancedSettings"
+                          >
+                            {{ $t('roleConfig.advancedSettings') }}
+                          </el-button>
                         </div>
                       </el-form-item>
                     </div>
@@ -318,6 +325,11 @@
       :providers="currentContextProviders"
       @confirm="handleUpdateContext"
     />
+    <tts-advanced-settings
+      :visible.sync="showTtsAdvancedDialog"
+      :settings="ttsSettings"
+      @save="handleTtsSettingsSave"
+    />
   </div>
 </template>
 
@@ -327,20 +339,30 @@ import { getServiceUrl } from "@/apis/api";
 import RequestService from "@/apis/httpRequest";
 import FunctionDialog from "@/components/FunctionDialog.vue";
 import ContextProviderDialog from "@/components/ContextProviderDialog.vue";
+import TtsAdvancedSettings from "@/components/TtsAdvancedSettings.vue";
 import HeaderBar from "@/components/HeaderBar.vue";
 import i18n from "@/i18n";
 import featureManager from "@/utils/featureManager"; 
 
 export default {
   name: "RoleConfigPage",
-  components: { HeaderBar, FunctionDialog, ContextProviderDialog },
+  components: { HeaderBar, FunctionDialog, ContextProviderDialog, TtsAdvancedSettings },
   data() {
     return {
       showContextProviderDialog: false,
+      showTtsAdvancedDialog: false,
+      ttsSettings: {
+        volume: 0,
+        speed: 0,
+        pitch: 0
+      },
       form: {
         agentCode: "",
         agentName: "",
         ttsVoiceId: "",
+        ttsVolume: null,
+        ttsRate: null,
+        ttsPitch: null,
         chatHistoryConf: 0,
         systemPrompt: "",
         summaryMemory: "",
@@ -422,6 +444,17 @@ export default {
         }),
         contextProviders: this.currentContextProviders,
       };
+
+      // 只在用户设置了TTS参数时才传递（不为null/undefined）
+      if (this.form.ttsVolume !== null && this.form.ttsVolume !== undefined) {
+        configData.ttsVolume = this.form.ttsVolume;
+      }
+      if (this.form.ttsRate !== null && this.form.ttsRate !== undefined) {
+        configData.ttsRate = this.form.ttsRate;
+      }
+      if (this.form.ttsPitch !== null && this.form.ttsPitch !== undefined) {
+        configData.ttsPitch = this.form.ttsPitch;
+      }
       Api.agent.updateAgentConfig(this.$route.query.agentId, configData, ({ data }) => {
         if (data.code === 0) {
           this.$message.success({
@@ -535,6 +568,14 @@ export default {
               intentModelId: data.data.intentModelId,
             },
           };
+
+          // 同步TTS设置到ttsSettings
+          this.ttsSettings = {
+            volume: this.form.ttsVolume || 0,
+            speed: this.form.ttsRate || 0,
+            pitch: this.form.ttsPitch || 0
+          };
+
           // 后端只给了最小映射：[{ id, agentId, pluginId }, ...]
           const savedMappings = data.data.functions || [];
           
@@ -696,6 +737,13 @@ export default {
       if (!currentVoiceSupportsLanguage) {
         this.form.ttsVoiceId = filteredVoices.length > 0 ? filteredVoices[0].id : '';
       }
+
+      // 同步到ttsSettings（如果值为null，使用0作为显示默认值，但不修改form中的值）
+      this.ttsSettings = {
+        volume: this.form.ttsVolume !== null && this.form.ttsVolume !== undefined ? this.form.ttsVolume : 0,
+        speed: this.form.ttsRate !== null && this.form.ttsRate !== undefined ? this.form.ttsRate : 0,
+        pitch: this.form.ttsPitch !== null && this.form.ttsPitch !== undefined ? this.form.ttsPitch : 0
+      };
     },
 
     getFunctionDisplayChar(name) {
@@ -763,6 +811,16 @@ export default {
     openContextProviderDialog() {
       this.showContextProviderDialog = true;
     },
+    openTtsAdvancedSettings() {
+      this.showTtsAdvancedDialog = true;
+    },
+    handleTtsSettingsSave(settings) {
+      // 保存TTS设置
+      this.ttsSettings = { ...settings };
+      this.form.ttsVolume = settings.volume;
+      this.form.ttsRate = settings.speed;
+      this.form.ttsPitch = settings.pitch;
+    },
     handleUpdateContext(providers) {
       this.currentContextProviders = providers;
     },
@@ -1316,6 +1374,15 @@ export default {
   margin-bottom: 0;
 }
 
+.model-row .language-select-item {
+  flex: 0 0 35%;
+  max-width: 35%;
+}
+
+.model-row .language-select-item .language-select {
+  width: 100%;
+}
+
 .model-row .el-form-item__label {
   font-size: 12px !important;
   color: #3d4566 !important;
@@ -1491,4 +1558,30 @@ export default {
     text-decoration: underline;
   }
 }
+
+.slider-wrapper {
+  width: 100%;
+  padding-right: 12px;
+}
+
+.slider-hint {
+  display: block;
+  font-size: 12px;
+  color: #909399;
+  margin-top: 4px;
+  line-height: 1.5;
+}
+
+.tts-slider {
+  width: 100%;
+}
+
+.tts-slider ::v-deep .el-slider__input {
+  width: 80px;
+}
+
+.tts-slider ::v-deep .el-input__inner {
+  text-align: center;
+  padding: 0 8px;
+}
 </style>

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))