feat: 添加本地tts支援面板的"角色音色"

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

@@ -66,6 +66,7 @@ public class ConfigServiceImpl implements ConfigService {
                 null,
                 null,
                 null,
+                null,
                 agent.getVadModelId(),
                 agent.getAsrModelId(),
                 null,
@@ -102,9 +103,11 @@ public class ConfigServiceImpl implements ConfigService {
         }
         // 获取音色信息
         String voice = null;
+        String voiceRemark = null;
         TimbreDetailsVO timbre = timbreService.get(agent.getTtsVoiceId());
         if (timbre != null) {
             voice = timbre.getTtsVoice();
+            voiceRemark = timbre.getRemark();
         }
         // 构建返回数据
         Map<String, Object> result = new HashMap<>();
@@ -138,6 +141,7 @@ public class ConfigServiceImpl implements ConfigService {
                 agent.getSystemPrompt(),
                 agent.getSummaryMemory(),
                 voice,
+                voiceRemark,
                 agent.getVadModelId(),
                 agent.getAsrModelId(),
                 agent.getLlmModelId(),
@@ -154,7 +158,7 @@ public class ConfigServiceImpl implements ConfigService {
     /**
      * 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) {
@@ -227,6 +231,7 @@ public class ConfigServiceImpl implements ConfigService {
      * 
      * @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
@@ -240,6 +245,7 @@ public class ConfigServiceImpl implements ConfigService {
             String prompt,
             String summaryMemory,
             String voice,
+            String voiceRemark,
             String vadModelId,
             String asrModelId,
             String llmModelId,
@@ -265,8 +271,9 @@ public class ConfigServiceImpl implements ConfigService {
             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) {
+                if ("TTS".equals(modelTypes[i])){
-                    ((Map<String, Object>) model.getConfigJson()).put("private_voice", voice);
+                    if (voice != null) ((Map<String, Object>) model.getConfigJson()).put("private_voice", voice);
+                    if (voiceRemark != null) ((Map<String, Object>) model.getConfigJson()).put("voice_remark", voiceRemark);
                 }
                 // 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/xiaozhi-server/core/providers/tts/fishspeech.py

@@ -129,6 +129,13 @@ 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

@@ -67,6 +67,14 @@ 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

@@ -34,6 +34,14 @@ 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,