Merge pull request #1518 from shane04111/add_local_tts_change_voice

update: 添加本地tts支援面板的"角色音色"

Author: openrz

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

@@ -72,6 +72,8 @@ public Object getConfig(Boolean isCache) {
                 null,
                 null,
                 null,
+                null,
+                null,
                 agent.getVadModelId(),
                 agent.getAsrModelId(),
                 null,
@@ -108,9 +110,13 @@ public Map<String, Object> getAgentModels(String macAddress, Map<String, String>
         }
         // 获取音色信息
         String voice = null;
+        String referenceAudio = null;
+        String referenceText = null;
         TimbreDetailsVO timbre = timbreService.get(agent.getTtsVoiceId());
         if (timbre != null) {
             voice = timbre.getTtsVoice();
+            referenceAudio = timbre.getReferenceAudio();
+            referenceText = timbre.getReferenceText();
         }
         // 构建返回数据
         Map<String, Object> result = new HashMap<>();
@@ -163,6 +169,8 @@ public Map<String, Object> getAgentModels(String macAddress, Map<String, String>
                 agent.getSystemPrompt(),
                 agent.getSummaryMemory(),
                 voice,
+                referenceAudio,
+                referenceText,
                 agent.getVadModelId(),
                 agent.getAsrModelId(),
                 agent.getLlmModelId(),
@@ -179,7 +187,7 @@ public Map<String, Object> getAgentModels(String macAddress, Map<String, String>
     /**
      * 构建配置信息
      * 
-     * @param paramsList 系统参数列表
+     * @param config 系统参数列表
      * @return 配置信息
      */
     private Object buildConfig(Map<String, Object> config) {
@@ -250,21 +258,25 @@ private Object buildConfig(Map<String, Object> config) {
     /**
      * 构建模块配置
      * 
-     * @param prompt        提示词
-     * @param voice         音色
-     * @param vadModelId    VAD模型ID
-     * @param asrModelId    ASR模型ID
-     * @param llmModelId    LLM模型ID
-     * @param ttsModelId    TTS模型ID
-     * @param memModelId    记忆模型ID
-     * @param intentModelId 意图模型ID
-     * @param result        结果Map
+     * @param prompt            提示词
+     * @param voice             音色
+     * @param referenceAudio    参考音频路径
+     * @param referenceText     参考文本
+     * @param vadModelId        VAD模型ID
+     * @param asrModelId        ASR模型ID
+     * @param llmModelId        LLM模型ID
+     * @param ttsModelId        TTS模型ID
+     * @param memModelId        记忆模型ID
+     * @param intentModelId     意图模型ID
+     * @param result            结果Map
      */
     private void buildModuleConfig(
             String assistantName,
             String prompt,
             String summaryMemory,
             String voice,
+            String referenceAudio,
+            String referenceText,
             String vadModelId,
             String asrModelId,
             String llmModelId,
@@ -290,8 +302,10 @@ private void buildModuleConfig(
             if (model.getConfigJson() != null) {
                 typeConfig.put(model.getId(), model.getConfigJson());
                 // 如果是TTS类型，添加private_voice属性
-                if ("TTS".equals(modelTypes[i]) && voice != null) {
-                    ((Map<String, Object>) model.getConfigJson()).put("private_voice", voice);
+                if ("TTS".equals(modelTypes[i])){
+                    if (voice != null) ((Map<String, Object>) model.getConfigJson()).put("private_voice", voice);
+                    if (referenceAudio != null) ((Map<String, Object>) model.getConfigJson()).put("ref_audio", referenceAudio);
+                    if (referenceText != null) ((Map<String, Object>) model.getConfigJson()).put("ref_text", referenceText);
                 }
                 // 如果是Intent类型，且type=intent_llm，则给他添加附加模型
                 if ("Intent".equals(modelTypes[i])) {

main/manager-api/src/main/java/xiaozhi/modules/timbre/dto/TimbreDataDTO.java

@@ -26,6 +26,12 @@ public class TimbreDataDTO {
     @Schema(description = "备注")
     private String remark;
 
+    @Schema(description = "参考音频路径")
+    private String referenceAudio;
+
+    @Schema(description = "參考文本")
+    private String referenceText;
+
     @Schema(description = "排序")
     @Min(value = 0, message = "{sort.number}")
     private long sort;

main/manager-api/src/main/java/xiaozhi/modules/timbre/entity/TimbreEntity.java

@@ -34,6 +34,12 @@ public class TimbreEntity {
     @Schema(description = "备注")
     private String remark;
 
+    @Schema(description = "参考音频路径")
+    private String referenceAudio;
+
+    @Schema(description = "參考文本")
+    private String referenceText;
+
     @Schema(description = "排序")
     private long sort;
 

main/manager-api/src/main/java/xiaozhi/modules/timbre/vo/TimbreDetailsVO.java

@@ -25,6 +25,12 @@ public class TimbreDetailsVO implements Serializable {
     @Schema(description = "备注")
     private String remark;
 
+    @Schema(description = "参考音频路径")
+    private String referenceAudio;
+
+    @Schema(description = "參考文本")
+    private String referenceText;
+
     @Schema(description = "排序")
     private long sort;
 

main/manager-api/src/main/resources/db/changelog/202506091720.sql

@@ -0,0 +1,3 @@
+ALTER TABLE `ai_tts_voice`
+ADD COLUMN `reference_audio` VARCHAR(500) DEFAULT NULL COMMENT '参考音频路径' AFTER `remark`,
+ADD COLUMN `reference_text` VARCHAR(500) DEFAULT NULL COMMENT '参考文本' AFTER `reference_audio`;

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

@@ -205,6 +205,13 @@ databaseChangeLog:
         - sqlFile:
             encoding: utf8
             path: classpath:db/changelog/202506080955.sql
+  - changeSet:
+      id: 202506091720
+      author: shane0411
+      changes:
+        - sqlFile:
+            encoding: utf8
+            path: classpath:db/changelog/202506091720.sql
   - changeSet:
       id: 202506161101
       author: hrz
@@ -232,4 +239,4 @@ databaseChangeLog:
       changes:
         - sqlFile:
             encoding: utf8
-            path: classpath:db/changelog/202506261637.sql
+            path: classpath:db/changelog/202506261637.sql

main/manager-web/src/apis/module/timbre.js

@@ -34,6 +34,8 @@ export default {
                 languages: params.languageType,
                 name: params.voiceName,
                 remark: params.remark,
+                referenceAudio: params.referenceAudio,
+                referenceText: params.referenceText,
                 sort: params.sort,
                 ttsModelId: params.ttsModelId,
                 ttsVoice: params.voiceCode,
@@ -75,6 +77,8 @@ export default {
                 languages: params.languageType,
                 name: params.voiceName,
                 remark: params.remark,
+                referenceAudio: params.referenceAudio,
+                referenceText: params.referenceText,
                 ttsModelId: params.ttsModelId,
                 ttsVoice: params.voiceCode,
                 voiceDemo: params.voiceDemo || ''

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

@@ -74,6 +74,18 @@
               <span v-else>{{ scope.row.remark }}</span>
             </template>
           </el-table-column>
+          <el-table-column label="音频路径" align="center">
+            <template slot-scope="scope">
+              <el-input v-if="scope.row.editing" v-model="scope.row.referenceAudio" placeholder="这里是参考音频路径 (本地模型用)"></el-input>
+              <span v-else>{{ scope.row.referenceAudio }}</span>
+            </template>
+          </el-table-column>
+          <el-table-column label="音频文本" align="center">
+            <template slot-scope="scope">
+              <el-input v-if="scope.row.editing" v-model="scope.row.referenceText" placeholder="这里是参考音频文本 (本地模型用)"></el-input>
+              <span v-else>{{ scope.row.referenceText }}</span>
+            </template>
+          </el-table-column>
           <el-table-column label="操作" align="center" width="150">
             <template slot-scope="scope">
               <template v-if="!scope.row.editing">
@@ -206,6 +218,8 @@ export default {
               voiceName: item.name || '未命名音色',
               languageType: item.languages || '',
               remark: item.remark || '',
+              referenceAudio: item.referenceAudio || '',
+              referenceText: item.referenceText || '',
               voiceDemo: item.voiceDemo || '',
               selected: false,
               editing: false,
@@ -351,6 +365,8 @@ export default {
           voiceName: row.voiceName,
           languageType: row.languageType,
           remark: row.remark,
+          referenceAudio: row.referenceAudio,
+          referenceText: row.referenceText,
           ttsModelId: this.ttsModelId,
           voiceDemo: row.voiceDemo || '',
           sort: row.sort
@@ -432,6 +448,8 @@ export default {
         languageType: '中文',
         voiceDemo: '',
         remark: '',
+        referenceAudio: '',
+        referenceText: '',
         selected: false,
         editing: true,
         sort: maxSort + 1

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

@@ -85,8 +85,12 @@ def __init__(self, config, delete_audio_file):
         self.reference_id = (
             None if not config.get("reference_id") else config.get("reference_id")
         )
-        self.reference_audio = parse_string_to_list(config.get("reference_audio"))
-        self.reference_text = parse_string_to_list(config.get("reference_text"))
+        self.reference_audio = parse_string_to_list(
+             config.get('ref_audio')if config.get('ref_audio') else config.get("reference_audio")
+        )
+        self.reference_text = parse_string_to_list(
+             config.get('ref_text')if config.get('ref_text') else config.get("reference_text")
+        )
         self.format = config.get("response_format", "wav")
         self.audio_file_type = config.get("response_format", "wav")
         self.api_key = config.get("api_key", "YOUR_API_KEY")

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

@@ -12,8 +12,8 @@ def __init__(self, config, delete_audio_file):
         super().__init__(config, delete_audio_file)
         self.url = config.get("url")
         self.text_lang = config.get("text_lang", "zh")
-        self.ref_audio_path = config.get("ref_audio_path")
-        self.prompt_text = config.get("prompt_text")
+        self.ref_audio_path = config.get('ref_audio') if config.get('ref_audio') else config.get("ref_audio_path")
+        self.prompt_text = config.get('ref_text') if config.get('ref_text') else config.get("prompt_text")
         self.prompt_lang = config.get("prompt_lang", "zh")
 
         # 处理空字符串的情况