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
2026-07-22 23:23:55 +08:00 · 2025-06-09 19:18:58 +08:00
parent be6fba5963
commit 2eb5539c9b
11 changed files with 83 additions and 45 deletions
@@ -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])) {
@@ -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;
@@ -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;

@@ -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;

@@ -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`;
@@ -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