feat: 新增音频路径與音频文本欄位，提供給本地tts選取音色

https://github.com/xinnan-tech/xiaozhi-esp32-server/issues/1503#issuecomment-2954952028

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

@@ -67,6 +67,7 @@ public class ConfigServiceImpl implements ConfigService {
                 null,
                 null,
                 null,
+                null,
                 agent.getVadModelId(),
                 agent.getAsrModelId(),
                 null,
@@ -103,11 +104,13 @@ public class ConfigServiceImpl implements ConfigService {
         }
         // 获取音色信息
         String voice = null;
-        String voiceRemark = null;
+        String referenceAudio = null;
+        String referenceText = null;
         TimbreDetailsVO timbre = timbreService.get(agent.getTtsVoiceId());
         if (timbre != null) {
             voice = timbre.getTtsVoice();
-            voiceRemark = timbre.getRemark();
+            referenceAudio = timbre.getReferenceAudio();
+            referenceText = timbre.getReferenceText();
         }
         // 构建返回数据
         Map<String, Object> result = new HashMap<>();
@@ -141,7 +144,8 @@ public class ConfigServiceImpl implements ConfigService {
                 agent.getSystemPrompt(),
                 agent.getSummaryMemory(),
                 voice,
-                voiceRemark,
+                referenceAudio,
+                referenceText,
                 agent.getVadModelId(),
                 agent.getAsrModelId(),
                 agent.getLlmModelId(),
@@ -229,23 +233,25 @@ public class ConfigServiceImpl implements ConfigService {
     /**
      * 构建模块配置
      * 
-     * @param prompt        提示词
-     * @param voice         音色
-     * @param voiceRemark   備註
-     * @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 voiceRemark,
+            String referenceAudio,
+            String referenceText,
             String vadModelId,
             String asrModelId,
             String llmModelId,
@@ -273,7 +279,8 @@ public class ConfigServiceImpl implements ConfigService {
                 // 如果是TTS类型，添加private_voice属性
                 if ("TTS".equals(modelTypes[i])){
                     if (voice != null) ((Map<String, Object>) model.getConfigJson()).put("private_voice", voice);
-                    if (voiceRemark != null) ((Map<String, Object>) model.getConfigJson()).put("voice_remark", voiceRemark);
+                    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

@@ -204,4 +204,11 @@ databaseChangeLog:
       changes:
         - sqlFile:
             encoding: utf8
-            path: classpath:db/changelog/202506080955.sql
+            path: classpath:db/changelog/202506080955.sql
+  - changeSet:
+      id: 202506091720
+      author: shane0411
+      changes:
+        - sqlFile:
+            encoding: utf8
+            path: classpath:db/changelog/202506091720.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"></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"></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 @@ class TTSProvider(TTSProviderBase):
         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")
@@ -129,13 +133,6 @@ class TTSProvider(TTSProviderBase):
         self.use_memory_cache = config.get("use_memory_cache", "on")
         self.seed = int(config.get("seed")) if config.get("seed") else None
         self.api_url = config.get("api_url", "http://127.0.0.1:8080/v1/tts")
-        self.get_voice_data(config)
-
-    def get_voice_data(self, config: dict):
-        if not config.get('private_voice', '') and not config.get('voice_remark', ''):
-            return
-        self.reference_audio = config.get('private_voice')
-        self.reference_text = config.get('voice_remark')
 
     async def text_to_speak(self, text, output_file):
         # Prepare reference data

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

@@ -12,8 +12,8 @@ class TTSProvider(TTSProviderBase):
         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
@@ -67,14 +67,6 @@ class TTSProvider(TTSProviderBase):
         )
         self.audio_file_type = config.get("format", "wav")
 
-        self.get_voice_data(config)
-
-    def get_voice_data(self, config: dict):
-        if not config.get('private_voice', '') and not config.get('voice_remark', ''):
-            return
-        self.ref_audio_path = config.get('private_voice')
-        self.prompt_text = config.get('voice_remark')
-
     async def text_to_speak(self, text, output_file):
         request_json = {
             "text": text,

main/xiaozhi-server/core/providers/tts/gpt_sovits_v3.py

@@ -11,8 +11,8 @@ class TTSProvider(TTSProviderBase):
     def __init__(self, config, delete_audio_file):
         super().__init__(config, delete_audio_file)
         self.url = config.get("url")
-        self.refer_wav_path = config.get("refer_wav_path")
-        self.prompt_text = config.get("prompt_text")
+        self.refer_wav_path = config.get('ref_audio')if config.get('ref_audio') else config.get("refer_wav_path")
+        self.prompt_text = config.get('ref_text')if config.get('ref_text') else config.get("prompt_text")
         self.prompt_language = config.get("prompt_language")
         self.text_language = config.get("text_language", "audo")
 
@@ -34,14 +34,6 @@ class TTSProvider(TTSProviderBase):
         self.if_sr = str(config.get("if_sr", False)).lower() in ("true", "1", "yes")
         self.audio_file_type = config.get("format", "wav")
 
-        self.get_voice_data(config)
-
-    def get_voice_data(self, config: dict):
-        if not config.get('private_voice', '') and not config.get('voice_remark', ''):
-            return
-        self.refer_wav_path = config.get('private_voice')
-        self.prompt_text = config.get('voice_remark')
-
     async def text_to_speak(self, text, output_file):
         request_params = {
             "refer_wav_path": self.refer_wav_path,