Merge pull request #1383 from xinnan-tech/tts-response

TTS流式框架改造：支持豆包语音双流式+支持传统非流式

.gitignore

@@ -107,6 +107,7 @@ celerybeat.pid
 *.sage.py
 
 # Environments
+.env
 .venv
 env/
 venv/
@@ -145,24 +146,31 @@ tmp
 .history
 .DS_Store
 main/xiaozhi-server/data
-main/xiaozhi-server/config/assets/wakeup_words.*
+
 main/manager-web/node_modules
 .config.yaml
 .secrets.yaml
 .private_config.yaml
+.env.development
 
 # model files
 main/xiaozhi-server/models/SenseVoiceSmall/model.pt
 main/xiaozhi-server/models/sherpa-onnx*
+/main/xiaozhi-server/audio_ref/
+/audio_ref/
+/asr-models/iic/SenseVoiceSmall/
+/main/xiaozhi-server/asr-models/iic/SenseVoiceSmall/
+/models/SenseVoiceSmall/model.pt
 my_wakeup_words.mp3
 !main/xiaozhi-server/config/assets/bind_code.wav
+!main/xiaozhi-server/config/assets/wakeup_words.wav
 !main/xiaozhi-server/config/assets/bind_not_found.wav
 !main/xiaozhi-server/config/assets/bind_code/*.wav
 !main/xiaozhi-server/config/assets/max_output_size.wav
 main/manager-api/.vscode
-
 # Ignore webpack cache directory
 main/manager-web/.webpack_cache/
 main/xiaozhi-server/mysql
 uploadfile
+*.json
 .vscode

main/manager-api/src/main/java/xiaozhi/common/constant/Constant.java

@@ -227,7 +227,7 @@ public interface Constant {
     /**
      * 版本号
      */
-    public static final String VERSION = "0.4.4";
+    public static final String VERSION = "0.5.1";
 
     /**
      * 无效固件URL

main/manager-api/src/main/java/xiaozhi/common/exception/RenExceptionHandler.java

@@ -4,7 +4,6 @@ import java.util.List;
 import java.util.Objects;
 
 import org.apache.shiro.authz.UnauthorizedException;
-import org.springframework.context.support.DefaultMessageSourceResolvable;
 import org.springframework.dao.DuplicateKeyException;
 import org.springframework.validation.ObjectError;
 import org.springframework.web.bind.MethodArgumentNotValidException;

main/manager-api/src/main/resources/db/changelog/202505271412.sql

@@ -1,4 +0,0 @@
--- 本地短期记忆配置可以设置独立的LLM
-
-update `ai_model_provider` set fields =  '[{"key":"llm","label":"LLM模型","type":"string"}]' where  id = 'SYSTEM_Memory_mem_local_short';
-update `ai_model_config` set config_json =  '{\"type\": \"mem_local_short\", \"llm\": \"LLM_ChatGLMLLM\"}' where  id = 'Memory_mem_local_short';

main/manager-api/src/main/resources/db/changelog/202505271414.sql

@@ -0,0 +1,51 @@
+-- 本地短期记忆配置可以设置独立的LLM
+update `ai_model_provider` set fields =  '[{"key":"llm","label":"LLM模型","type":"string"}]' where  id = 'SYSTEM_Memory_mem_local_short';
+update `ai_model_config` set config_json =  '{\"type\": \"mem_local_short\", \"llm\": \"LLM_ChatGLMLLM\"}' where  id = 'Memory_mem_local_short';
+
+-- 增加火山双流式TTS供应器和模型配置
+delete from `ai_model_provider` where id = 'SYSTEM_TTS_HSDSTTS';
+INSERT INTO `ai_model_provider` (`id`, `model_type`, `provider_code`, `name`, `fields`, `sort`, `creator`, `create_date`, `updater`, `update_date`) VALUES
+('SYSTEM_TTS_HSDSTTS', 'TTS', 'huoshan_double_stream', '火山双流式语音合成', '[{"key":"ws_url","label":"WebSocket地址","type":"string"},{"key":"appid","label":"应用ID","type":"string"},{"key":"access_token","label":"访问令牌","type":"string"},{"key":"resource_id","label":"资源ID","type":"string"},{"key":"speaker","label":"默认音色","type":"string"}]', 13, 1, NOW(), 1, NOW());
+
+delete from `ai_model_config` where id = 'TTS_HuoshanDoubleStreamTTS';
+INSERT INTO `ai_model_config` VALUES ('TTS_HuoshanDoubleStreamTTS', 'TTS', 'HuoshanDoubleStreamTTS', '火山双流式语音合成', 0, 1, '{\"type\": \"huoshan_double_stream\", \"ws_url\": \"wss://openspeech.bytedance.com/api/v3/tts/bidirection\", \"appid\": \"你的火山引擎语音合成服务appid\", \"access_token\": \"你的火山引擎语音合成服务access_token\", \"resource_id\": \"volc.service_type.10029\", \"speaker\": \"zh_female_wanwanxiaohe_moon_bigtts\"}', NULL, NULL, 16, NULL, NULL, NULL, NULL);
+
+-- 火山双流式TT模型配置说明文档
+UPDATE `ai_model_config` SET 
+`doc_link` = 'https://console.volcengine.com/speech/service/10007',
+`remark` = '火山引擎语音合成服务配置说明：
+1. 访问 https://www.volcengine.com/ 注册并开通火山引擎账号
+2. 访问 https://console.volcengine.com/speech/service/10007 开通语音合成大模型，购买音色
+3. 在页面底部获取appid和access_token
+5. 资源ID固定为：volc.service_type.10029（大模型语音合成及混音）
+6. 填入配置文件中' WHERE `id` = 'TTS_HuoshanDoubleStreamTTS';
+
+
+-- 添加火山双流式TTS音色
+delete from `ai_tts_voice` where tts_model_id = 'TTS_HuoshanDoubleStreamTTS';
+INSERT INTO `ai_tts_voice` VALUES ('TTS_HuoshanDoubleStreamTTS_0001', 'TTS_HuoshanDoubleStreamTTS', '爽快思思/Skye', 'zh_female_shuangkuaisisi_moon_bigtts', '中文、英文', 'https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_hz_ihsph/ljhwZthlaukjlkulzlp/portal/bigtts/Skye.mp3', NULL, 1, NULL, NULL, NULL, NULL);
+INSERT INTO `ai_tts_voice` VALUES ('TTS_HuoshanDoubleStreamTTS_0002', 'TTS_HuoshanDoubleStreamTTS', '温暖阿虎/Alvin', 'zh_male_wennuanahu_moon_bigtts', '中文、英文', 'https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_hz_ihsph/ljhwZthlaukjlkulzlp/portal/bigtts/Alvin.mp3', NULL, 2, NULL, NULL, NULL, NULL);
+INSERT INTO `ai_tts_voice` VALUES ('TTS_HuoshanDoubleStreamTTS_0003', 'TTS_HuoshanDoubleStreamTTS', '少年梓辛/Brayan', 'zh_male_shaonianzixin_moon_bigtts', '中文、英文', 'https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_hz_ihsph/ljhwZthlaukjlkulzlp/portal/bigtts/Brayan.mp3', NULL, 3, NULL, NULL, NULL, NULL);
+INSERT INTO `ai_tts_voice` VALUES ('TTS_HuoshanDoubleStreamTTS_0004', 'TTS_HuoshanDoubleStreamTTS', '邻家女孩', 'zh_female_linjianvhai_moon_bigtts', '中文', 'https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_hz_ihsph/ljhwZthlaukjlkulzlp/portal/bigtts/%E9%82%BB%E5%AE%B6%E5%A5%B3%E5%AD%A9.mp3', NULL, 4, NULL, NULL, NULL, NULL);
+INSERT INTO `ai_tts_voice` VALUES ('TTS_HuoshanDoubleStreamTTS_0005', 'TTS_HuoshanDoubleStreamTTS', '渊博小叔', 'zh_male_yuanboxiaoshu_moon_bigtts', '中文', 'https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_hz_ihsph/ljhwZthlaukjlkulzlp/portal/bigtts/%E6%B8%8A%E5%8D%9A%E5%B0%8F%E5%8F%94.mp3', NULL, 5, NULL, NULL, NULL, NULL);
+INSERT INTO `ai_tts_voice` VALUES ('TTS_HuoshanDoubleStreamTTS_0006', 'TTS_HuoshanDoubleStreamTTS', '阳光青年', 'zh_male_yangguangqingnian_moon_bigtts', '中文', 'https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_hz_ihsph/ljhwZthlaukjlkulzlp/portal/bigtts/%E9%98%B3%E5%85%89%E9%9D%92%E5%B9%B4.mp3', NULL, 6, NULL, NULL, NULL, NULL);
+INSERT INTO `ai_tts_voice` VALUES ('TTS_HuoshanDoubleStreamTTS_0007', 'TTS_HuoshanDoubleStreamTTS', '京腔侃爷/Harmony', 'zh_male_jingqiangkanye_moon_bigtts', '中文、英文', 'https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_hz_ihsph/ljhwZthlaukjlkulzlp/portal/bigtts/Harmony.mp3', NULL, 7, NULL, NULL, NULL, NULL);
+INSERT INTO `ai_tts_voice` VALUES ('TTS_HuoshanDoubleStreamTTS_0008', 'TTS_HuoshanDoubleStreamTTS', '湾湾小何', 'zh_female_wanwanxiaohe_moon_bigtts', '中文', 'https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_hz_ihsph/ljhwZthlaukjlkulzlp/portal/bigtts/%E6%B9%BE%E6%B9%BE%E5%B0%8F%E4%BD%95.mp3', NULL, 8, NULL, NULL, NULL, NULL);
+INSERT INTO `ai_tts_voice` VALUES ('TTS_HuoshanDoubleStreamTTS_0009', 'TTS_HuoshanDoubleStreamTTS', '湾区大叔', 'zh_female_wanqudashu_moon_bigtts', '中文', 'https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_hz_ihsph/ljhwZthlaukjlkulzlp/portal/bigtts/%E6%B9%BE%E5%8C%BA%E5%A4%A7%E5%8F%94.mp3', NULL, 9, NULL, NULL, NULL, NULL);
+INSERT INTO `ai_tts_voice` VALUES ('TTS_HuoshanDoubleStreamTTS_0010', 'TTS_HuoshanDoubleStreamTTS', '呆萌川妹', 'zh_female_daimengchuanmei_moon_bigtts', '中文', 'https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_hz_ihsph/ljhwZthlaukjlkulzlp/portal/bigtts/%E5%91%86%E8%90%8C%E5%B7%9D%E5%A6%B9.mp3', NULL, 10, NULL, NULL, NULL, NULL);
+INSERT INTO `ai_tts_voice` VALUES ('TTS_HuoshanDoubleStreamTTS_0011', 'TTS_HuoshanDoubleStreamTTS', '广州德哥', 'zh_male_guozhoudege_moon_bigtts', '中文', 'https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_hz_ihsph/ljhwZthlaukjlkulzlp/portal/bigtts/%E5%B9%BF%E5%B7%9E%E5%BE%B7%E5%93%A5.mp3', NULL, 11, NULL, NULL, NULL, NULL);
+INSERT INTO `ai_tts_voice` VALUES ('TTS_HuoshanDoubleStreamTTS_0012', 'TTS_HuoshanDoubleStreamTTS', '北京小爷', 'zh_male_beijingxiaoye_moon_bigtts', '中文', 'https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_hz_ihsph/ljhwZthlaukjlkulzlp/portal/bigtts/%E5%8C%97%E4%BA%AC%E5%B0%8F%E7%88%B7.mp3', NULL, 12, NULL, NULL, NULL, NULL);
+INSERT INTO `ai_tts_voice` VALUES ('TTS_HuoshanDoubleStreamTTS_0013', 'TTS_HuoshanDoubleStreamTTS', '浩宇小哥', 'zh_male_haoyuxiaoge_moon_bigtts', '中文', 'https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_hz_ihsph/ljhwZthlaukjlkulzlp/portal/bigtts/%E6%B5%A9%E5%AE%87%E5%B0%8F%E5%93%A5.mp3', NULL, 13, NULL, NULL, NULL, NULL);
+INSERT INTO `ai_tts_voice` VALUES ('TTS_HuoshanDoubleStreamTTS_0014', 'TTS_HuoshanDoubleStreamTTS', '广西远舟', 'zh_male_guangxiyuanzhou_moon_bigtts', '中文', 'https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_hz_ihsph/ljhwZthlaukjlkulzlp/portal/bigtts/%E5%B9%BF%E8%A5%BF%E8%BF%9C%E8%88%9F.mp3', NULL, 14, NULL, NULL, NULL, NULL);
+INSERT INTO `ai_tts_voice` VALUES ('TTS_HuoshanDoubleStreamTTS_0015', 'TTS_HuoshanDoubleStreamTTS', '妹坨洁儿', 'zh_female_meituojieer_moon_bigtts', '中文', 'https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_hz_ihsph/ljhwZthlaukjlkulzlp/portal/bigtts/%E5%A6%B9%E5%9D%A8%E6%B4%81%E5%84%BF.mp3', NULL, 15, NULL, NULL, NULL, NULL);
+INSERT INTO `ai_tts_voice` VALUES ('TTS_HuoshanDoubleStreamTTS_0016', 'TTS_HuoshanDoubleStreamTTS', '豫州子轩', 'zh_male_yuzhouzixuan_moon_bigtts', '中文', 'https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_hz_ihsph/ljhwZthlaukjlkulzlp/portal/bigtts/%E8%B1%AB%E5%B7%9E%E5%AD%90%E8%BD%A9.mp3', NULL, 16, NULL, NULL, NULL, NULL);
+INSERT INTO `ai_tts_voice` VALUES ('TTS_HuoshanDoubleStreamTTS_0017', 'TTS_HuoshanDoubleStreamTTS', '高冷御姐', 'zh_female_gaolengyujie_moon_bigtts', '中文', 'https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_hz_ihsph/ljhwZthlaukjlkulzlp/portal/bigtts/%E9%AB%98%E5%86%B7%E5%BE%A1%E5%A7%90.mp3', NULL, 17, NULL, NULL, NULL, NULL);
+INSERT INTO `ai_tts_voice` VALUES ('TTS_HuoshanDoubleStreamTTS_0018', 'TTS_HuoshanDoubleStreamTTS', '傲娇霸总', 'zh_male_aojiaobazong_moon_bigtts', '中文', 'https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_hz_ihsph/ljhwZthlaukjlkulzlp/portal/bigtts/%E5%82%B2%E5%A8%87%E9%9C%B8%E6%80%BB.mp3', NULL, 18, NULL, NULL, NULL, NULL);
+INSERT INTO `ai_tts_voice` VALUES ('TTS_HuoshanDoubleStreamTTS_0019', 'TTS_HuoshanDoubleStreamTTS', '魅力女友', 'zh_female_meilinvyou_moon_bigtts', '中文', 'https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_hz_ihsph/ljhwZthlaukjlkulzlp/portal/bigtts/%E9%AD%85%E5%8A%9B%E5%A5%B3%E5%8F%8B.mp3', NULL, 19, NULL, NULL, NULL, NULL);
+INSERT INTO `ai_tts_voice` VALUES ('TTS_HuoshanDoubleStreamTTS_0020', 'TTS_HuoshanDoubleStreamTTS', '深夜播客', 'zh_male_shenyeboke_moon_bigtts', '中文', 'https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_hz_ihsph/ljhwZthlaukjlkulzlp/portal/bigtts/%E6%B7%B1%E5%A4%9C%E6%92%AD%E5%AE%A2.mp3', NULL, 20, NULL, NULL, NULL, NULL);
+INSERT INTO `ai_tts_voice` VALUES ('TTS_HuoshanDoubleStreamTTS_0021', 'TTS_HuoshanDoubleStreamTTS', '柔美女友', 'zh_female_sajiaonvyou_moon_bigtts', '中文', 'https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_hz_ihsph/ljhwZthlaukjlkulzlp/portal/bigtts/%E6%9F%94%E7%BE%8E%E5%A5%B3%E5%8F%8B.mp3', NULL, 21, NULL, NULL, NULL, NULL);
+INSERT INTO `ai_tts_voice` VALUES ('TTS_HuoshanDoubleStreamTTS_0022', 'TTS_HuoshanDoubleStreamTTS', '撒娇学妹', 'zh_female_yuanqinvyou_moon_bigtts', '中文', 'https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_hz_ihsph/ljhwZthlaukjlkulzlp/portal/bigtts/%E6%92%92%E5%A8%87%E5%AD%A6%E5%A6%B9.mp3', NULL, 22, NULL, NULL, NULL, NULL);
+INSERT INTO `ai_tts_voice` VALUES ('TTS_HuoshanDoubleStreamTTS_0023', 'TTS_HuoshanDoubleStreamTTS', 'かずね（和音）', 'multi_male_jingqiangkanye_moon_bigtts', '日语、西语', 'https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_hz_ihsph/ljhwZthlaukjlkulzlp/portal/bigtts/Javier.wav', NULL, 23, NULL, NULL, NULL, NULL);
+INSERT INTO `ai_tts_voice` VALUES ('TTS_HuoshanDoubleStreamTTS_0024', 'TTS_HuoshanDoubleStreamTTS', 'はるこ（晴子）', 'multi_female_shuangkuaisisi_moon_bigtts', '日语、西语', 'https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_hz_ihsph/ljhwZthlaukjlkulzlp/portal/bigtts/Esmeralda.mp3', NULL, 24, NULL, NULL, NULL, NULL);
+INSERT INTO `ai_tts_voice` VALUES ('TTS_HuoshanDoubleStreamTTS_0025', 'TTS_HuoshanDoubleStreamTTS', 'あけみ（朱美）', 'multi_female_gaolengyujie_moon_bigtts', '日语', 'https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_hz_ihsph/ljhwZthlaukjlkulzlp/portal/bigtts/%E6%9C%B1%E7%BE%8E.mp3', NULL, 25, NULL, NULL, NULL, NULL);
+INSERT INTO `ai_tts_voice` VALUES ('TTS_HuoshanDoubleStreamTTS_0026', 'TTS_HuoshanDoubleStreamTTS', 'ひろし（広志）', 'multi_male_wanqudashu_moon_bigtts', '日语、西语', 'https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_hz_ihsph/ljhwZthlaukjlkulzlp/portal/bigtts/Roberto.wav', NULL, 26, NULL, NULL, NULL, NULL);

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

@@ -164,9 +164,9 @@ databaseChangeLog:
             encoding: utf8
             path: classpath:db/changelog/202505151451.sql
   - changeSet:
-      id: 202505271412
+      id: 202505271414
       author: hrz
       changes:
         - sqlFile:
             encoding: utf8
-            path: classpath:db/changelog/202505271412.sql
+            path: classpath:db/changelog/202505271414.sql

main/xiaozhi-server/config.yaml

@@ -85,6 +85,7 @@ module_test:
 # 唤醒词，用于识别唤醒词还是讲话内容
 wakeup_words:
   - "你好小智"
+  - "嘿你好呀"
   - "你好小志"
   - "小爱同学"
   - "你好小鑫"
@@ -329,7 +330,7 @@ LLM:
     # 定义LLM API类型
     type: openai
     # 先开通服务，打开以下网址，开通的服务搜索Doubao-1.5-pro，开通它
-    # 开通改地址：https://console.volcengine.com/ark/region:ark+cn-beijing/openManagement?LLM=%7B%7D&OpenTokenDrawer=false
+    # 开通地址：https://console.volcengine.com/ark/region:ark+cn-beijing/openManagement?LLM=%7B%7D&OpenTokenDrawer=false
     # 免费额度500000token
     # 开通后，进入这里获取密钥：https://console.volcengine.com/ark/region:ark+cn-beijing/apiKey?apikey=%7B%7D
     base_url: https://ark.cn-beijing.volces.com/api/v3
@@ -456,6 +457,19 @@ TTS:
     speed_ratio: 1.0
     volume_ratio: 1.0
     pitch_ratio: 1.0
+  #火山tts，支持双向流式tts
+  HuoshanDoubleStreamTTS:
+    type: huoshan_double_stream
+    # 访问 https://console.volcengine.com/speech/service/10007 开通语音合成大模型，购买音色
+    # 在页面底部获取appid和access_token
+    # 资源ID固定为：volc.service_type.10029（大模型语音合成及混音）
+    # 如果是机智云，把接口地址换成wss://bytedance.gizwitsapi.com/api/v3/tts/bidirection
+    # 机智云不需要天填 appid
+    ws_url: wss://openspeech.bytedance.com/api/v3/tts/bidirection
+    appid: 你的火山引擎语音合成服务appid
+    access_token: 你的火山引擎语音合成服务access_token
+    resource_id: volc.service_type.10029
+    speaker: zh_female_wanwanxiaohe_moon_bigtts
   CosyVoiceSiliconflow:
     type: siliconflow
     # 硅基流动TTS

main/xiaozhi-server/config/logger.py

@@ -4,7 +4,7 @@ from loguru import logger
 from config.config_loader import load_config
 from config.settings import check_config_file
 
-SERVER_VERSION = "0.4.4"
+SERVER_VERSION = "0.5.1"
 
 
 def get_module_abbreviation(module_name, module_dict):

main/xiaozhi-server/core/connection.py

@@ -1,42 +1,40 @@
 import os
+import sys
 import copy
 import json
-import subprocess
-import sys
 import uuid
 import time
 import queue
 import asyncio
-import traceback
-
 import threading
+import traceback
+import subprocess
 import websockets
-from typing import Dict, Any
-from plugins_func.loadplugins import auto_import_modules
-from config.logger import setup_logging
-from config.config_loader import get_project_dir
-from core.utils import p3
-from core.utils.dialogue import Message, Dialogue
-from core.handle.textHandle import handleTextMessage
 from core.utils.util import (
-    get_string_no_punctuation_or_emoji,
     extract_json_from_string,
     initialize_modules,
     check_vad_update,
     check_asr_update,
     filter_sensitive_info,
+    initialize_tts,
 )
-from concurrent.futures import ThreadPoolExecutor, TimeoutError
+from typing import Dict, Any
-from core.handle.sendAudioHandle import sendAudioMessage
+from config.logger import setup_logging
-from core.handle.receiveAudioHandle import handleAudioMessage
+from core.mcp.manager import MCPManager
+from core.handle.reportHandle import report
+from core.providers.tts.default import DefaultTTS
+from concurrent.futures import ThreadPoolExecutor
+from core.utils.dialogue import Message, Dialogue
+from core.handle.textHandle import handleTextMessage
 from core.handle.functionHandler import FunctionHandler
+from plugins_func.loadplugins import auto_import_modules
 from plugins_func.register import Action, ActionResponse
 from core.auth import AuthMiddleware, AuthenticationError
-from core.mcp.manager import MCPManager
 from config.config_loader import get_private_config_from_api
+from core.handle.receiveAudioHandle import handleAudioMessage
+from core.providers.tts.dto.dto import ContentType, TTSMessageDTO, SentenceType
 from config.manage_api_client import DeviceNotFoundException, DeviceBindException
-from core.utils.output_counter import add_device_output
+
-from core.handle.reportHandle import enqueue_tts_report, report
 
 TAG = __name__
 
@@ -54,7 +52,6 @@ class ConnectionHandler:
         _vad,
         _asr,
         _llm,
-        _tts,
         _memory,
         _intent,
         server=None,
@@ -87,8 +84,6 @@ class ConnectionHandler:
         # 线程任务相关
         self.loop = asyncio.get_event_loop()
         self.stop_event = threading.Event()
-        self.tts_queue = queue.Queue()
-        self.audio_play_queue = queue.Queue()
         self.executor = ThreadPoolExecutor(max_workers=5)
 
         # 添加上报线程池
@@ -101,10 +96,10 @@ class ConnectionHandler:
         # 依赖的组件
         self.vad = None
         self.asr = None
+        self.tts = None
         self._asr = _asr
         self._vad = _vad
         self.llm = _llm
-        self.tts = _tts
         self.memory = _memory
         self.intent = _intent
 
@@ -120,12 +115,11 @@ class ConnectionHandler:
         self.asr_server_receive = True
 
         # llm相关变量
-        self.llm_finish_task = False
+        self.llm_finish_task = True
         self.dialogue = Dialogue()
 
         # tts相关变量
-        self.tts_first_text_index = -1
+        self.sentence_id = None
-        self.tts_last_text_index = -1
 
         # iot相关变量
         self.iot_descriptors = {}
@@ -196,17 +190,6 @@ class ConnectionHandler:
             self._initialize_private_config()
             # 异步初始化
             self.executor.submit(self._initialize_components)
-            # tts 消化线程
-            self.tts_priority_thread = threading.Thread(
-                target=self._tts_priority_thread, daemon=True
-            )
-            self.tts_priority_thread.start()
-
-            # 音频播放 消化线程
-            self.audio_play_priority_thread = threading.Thread(
-                target=self._audio_play_priority_thread, daemon=True
-            )
-            self.audio_play_priority_thread.start()
 
             try:
                 async for message in self.websocket:
@@ -315,25 +298,36 @@ class ConnectionHandler:
             )
 
     def _initialize_components(self):
-        """初始化组件"""
+        try:
-        if self.config.get("prompt") is not None:
+
-            self.prompt = self.config["prompt"]
+            """初始化组件"""
-            self.change_system_prompt(self.prompt)
+            if self.config.get("prompt") is not None:
-            self.logger.bind(tag=TAG).info(
+                self.prompt = self.config["prompt"]
-                f"初始化组件: prompt成功 {self.prompt[:50]}..."
+                self.change_system_prompt(self.prompt)
+                self.logger.bind(tag=TAG).info(
+                    f"初始化组件: prompt成功 {self.prompt[:50]}..."
+                )
+
+            """初始化本地组件"""
+            if self.vad is None:
+                self.vad = self._vad
+            if self.asr is None:
+                self.asr = self._asr
+            if self.tts is None:
+                self.tts = self._initialize_tts()
+            # 使用事件循环运行异步方法
+            asyncio.run_coroutine_threadsafe(
+                self.tts.open_audio_channels(self), self.loop
             )
 
-        """初始化本地组件"""
+            """加载记忆"""
-        if self.vad is None:
+            self._initialize_memory()
-            self.vad = self._vad
+            """加载意图识别"""
-        if self.asr is None:
+            self._initialize_intent()
-            self.asr = self._asr
+            """初始化上报线程"""
-        """加载记忆"""
+            self._init_report_threads()
-        self._initialize_memory()
+        except Exception as e:
-        """加载意图识别"""
+            self.logger.bind(tag=TAG).error(f"实例化组件失败: {e}")
-        self._initialize_intent()
-        """初始化上报线程"""
-        self._init_report_threads()
 
     def _init_report_threads(self):
         """初始化ASR和TTS上报线程"""
@@ -348,6 +342,17 @@ class ConnectionHandler:
             self.report_thread.start()
             self.logger.bind(tag=TAG).info("TTS上报线程已启动")
 
+    def _initialize_tts(self):
+        """初始化TTS"""
+        tts = None
+        if not self.need_bind:
+            tts = initialize_tts(self.config)
+
+        if tts is None:
+            tts = DefaultTTS(self.config, delete_audio_file=True)
+
+        return tts
+
     def _initialize_private_config(self):
         """如果是从配置文件获取，则进行二次实例化"""
         if not self.read_config_from_api:
@@ -540,7 +545,8 @@ class ConnectionHandler:
         self.dialogue.update_system_message(self.prompt)
 
     def chat(self, query, tool_call=False):
-        self.logger.bind(tag=TAG).debug(f"Chat: {query}")
+        self.logger.bind(tag=TAG).info(f"大模型收到用户消息: {query}")
+        self.llm_finish_task = False
 
         if not tool_call:
             self.dialogue.put(Message(role="user", content=query))
@@ -550,7 +556,6 @@ class ConnectionHandler:
         if self.intent_type == "function_call" and hasattr(self, "func_handler"):
             functions = self.func_handler.get_functions()
         response_message = []
-        processed_chars = 0  # 跟踪已处理的字符位置
 
         try:
             # 使用带记忆的对话
@@ -561,6 +566,9 @@ class ConnectionHandler:
                 )
                 memory_str = future.result()
 
+            uuid_str = str(uuid.uuid4()).replace("-", "")
+            self.sentence_id = uuid_str
+
             if functions is not None:
                 # 使用支持functions的streaming接口
                 llm_responses = self.llm.response_with_functions(
@@ -577,15 +585,13 @@ class ConnectionHandler:
             self.logger.bind(tag=TAG).error(f"LLM 处理出错 {query}: {e}")
             return None
 
-        self.llm_finish_task = False
-        text_index = 0
-
         # 处理流式响应
         tool_call_flag = False
         function_name = None
         function_id = None
         function_arguments = ""
         content_arguments = ""
+        text_index = 0
 
         for response in llm_responses:
             if self.intent_type == "function_call":
@@ -613,47 +619,26 @@ class ConnectionHandler:
             if content is not None and len(content) > 0:
                 if not tool_call_flag:
                     response_message.append(content)
-
                     if self.client_abort:
                         break
 
-                    end_time = time.time()
+                    if text_index == 0:
-                    # self.logger.bind(tag=TAG).debug(f"大模型返回时间: {end_time - start_time} 秒, 生成token={content}")
+                        self.tts.tts_text_queue.put(
-
+                            TTSMessageDTO(
-                    # 处理文本分段和TTS逻辑
+                                sentence_id=self.sentence_id,
-                    # 合并当前全部文本并处理未分割部分
+                                sentence_type=SentenceType.FIRST,
-                    full_text = "".join(response_message)
+                                content_type=ContentType.ACTION,
-                    current_text = full_text[processed_chars:]  # 从未处理的位置开始
-
-                    # 查找最后一个有效标点
-                    punctuations = ("。", ".", "？", "?", "！", "!", "；", ";", "：")
-                    last_punct_pos = -1
-                    number_flag = True
-                    for punct in punctuations:
-                        pos = current_text.rfind(punct)
-                        prev_char = current_text[pos - 1] if pos - 1 >= 0 else ""
-                        # 如果.前面是数字统一判断为小数
-                        if prev_char.isdigit() and punct == ".":
-                            number_flag = False
-                        if pos > last_punct_pos and number_flag:
-                            last_punct_pos = pos
-
-                    # 找到分割点则处理
-                    if last_punct_pos != -1:
-                        segment_text_raw = current_text[: last_punct_pos + 1]
-                        segment_text = get_string_no_punctuation_or_emoji(
-                            segment_text_raw
-                        )
-                        if segment_text:
-                            text_index += 1
-                            self.recode_first_last_text(segment_text, text_index)
-                            future = self.executor.submit(
-                                self.speak_and_play, None, segment_text, text_index
                             )
-                            self.tts_queue.put((future, text_index))
+                        )
-                            # 更新已处理字符位置
+                    self.tts.tts_text_queue.put(
-                            processed_chars += len(segment_text_raw)
+                        TTSMessageDTO(
-
+                            sentence_id=self.sentence_id,
+                            sentence_type=SentenceType.MIDDLE,
+                            content_type=ContentType.TEXT,
+                            content_detail=content,
+                        )
+                    )
+                    text_index += 1
         # 处理function call
         if tool_call_flag:
             bHasError = False
@@ -696,27 +681,21 @@ class ConnectionHandler:
                     result = self.func_handler.handle_llm_function_call(
                         self, function_call_data
                     )
-                self._handle_function_result(result, function_call_data, text_index + 1)
+                self._handle_function_result(result, function_call_data)
-
-        # 处理最后剩余的文本
-        full_text = "".join(response_message)
-        remaining_text = full_text[processed_chars:]
-        if remaining_text:
-            segment_text = get_string_no_punctuation_or_emoji(remaining_text)
-            if segment_text:
-                text_index += 1
-                self.recode_first_last_text(segment_text, text_index)
-                future = self.executor.submit(
-                    self.speak_and_play, None, segment_text, text_index
-                )
-                self.tts_queue.put((future, text_index))
 
         # 存储对话内容
         if len(response_message) > 0:
             self.dialogue.put(
                 Message(role="assistant", content="".join(response_message))
             )
-
+        if text_index > 0:
+            self.tts.tts_text_queue.put(
+                TTSMessageDTO(
+                    sentence_id=self.sentence_id,
+                    sentence_type=SentenceType.LAST,
+                    content_type=ContentType.ACTION,
+                )
+            )
         self.llm_finish_task = True
         self.logger.bind(tag=TAG).debug(
             json.dumps(self.dialogue.get_llm_dialogue(), indent=4, ensure_ascii=False)
@@ -766,12 +745,10 @@ class ConnectionHandler:
 
         return ActionResponse(action=Action.REQLLM, result="工具调用出错", response="")
 
-    def _handle_function_result(self, result, function_call_data, text_index):
+    def _handle_function_result(self, result, function_call_data):
         if result.action == Action.RESPONSE:  # 直接回复前端
             text = result.response
-            self.recode_first_last_text(text, text_index)
+            self.tts.tts_one_sentence(self, ContentType.TEXT, content_detail=text)
-            future = self.executor.submit(self.speak_and_play, None, text, text_index)
-            self.tts_queue.put((future, text_index))
             self.dialogue.put(Message(role="assistant", content=text))
         elif result.action == Action.REQLLM:  # 调用函数后再请求llm生成回复
             text = result.result
@@ -808,109 +785,11 @@ class ConnectionHandler:
                 self.chat(text, tool_call=True)
         elif result.action == Action.NOTFOUND or result.action == Action.ERROR:
             text = result.result
-            self.recode_first_last_text(text, text_index)
+            self.tts.tts_one_sentence(self, ContentType.TEXT, content_detail=text)
-            future = self.executor.submit(self.speak_and_play, None, text, text_index)
-            self.tts_queue.put((future, text_index))
             self.dialogue.put(Message(role="assistant", content=text))
         else:
             pass
 
-    def _tts_priority_thread(self):
-        while not self.stop_event.is_set():
-            text = None
-            try:
-                try:
-                    item = self.tts_queue.get(timeout=1)
-                    if item is None:
-                        continue
-                    future, text_index = item  # 解包获取 Future 和 text_index
-                except queue.Empty:
-                    if self.stop_event.is_set():
-                        break
-                    continue
-                if future is None:
-                    continue
-                text = None
-                audio_datas, tts_file = [], None
-                try:
-                    self.logger.bind(tag=TAG).debug("正在处理TTS任务...")
-                    tts_timeout = int(self.config.get("tts_timeout", 10))
-                    tts_file, text, _ = future.result(timeout=tts_timeout)
-                    if tts_file is None:
-                        self.logger.bind(tag=TAG).error(
-                            f"TTS出错： file is empty: {text_index}: {text}"
-                        )
-                    else:
-                        self.logger.bind(tag=TAG).debug(
-                            f"TTS生成：文件路径: {tts_file}"
-                        )
-                        if os.path.exists(tts_file):
-                            if tts_file.endswith(".p3"):
-                                audio_datas, _ = p3.decode_opus_from_file(tts_file)
-                            elif self.audio_format == "pcm":
-                                audio_datas, _ = self.tts.audio_to_pcm_data(tts_file)
-                            else:
-                                audio_datas, _ = self.tts.audio_to_opus_data(tts_file)
-                            # 在这里上报TTS数据
-                            enqueue_tts_report(
-                                self, tts_file if text is None else text, audio_datas
-                            )
-                        else:
-                            self.logger.bind(tag=TAG).error(
-                                f"TTS出错：文件不存在{tts_file}"
-                            )
-                except TimeoutError:
-                    self.logger.bind(tag=TAG).error("TTS超时")
-                except Exception as e:
-                    self.logger.bind(tag=TAG).error(f"TTS出错: {e}")
-                if not self.client_abort:
-                    # 如果没有中途打断就发送语音
-                    self.audio_play_queue.put((audio_datas, text, text_index))
-                if (
-                    self.tts.delete_audio_file
-                    and tts_file is not None
-                    and os.path.exists(tts_file)
-                    and tts_file.startswith(self.tts.output_file)
-                ):
-                    os.remove(tts_file)
-            except Exception as e:
-                self.logger.bind(tag=TAG).error(f"TTS任务处理错误: {e}")
-                self.clearSpeakStatus()
-                asyncio.run_coroutine_threadsafe(
-                    self.websocket.send(
-                        json.dumps(
-                            {
-                                "type": "tts",
-                                "state": "stop",
-                                "session_id": self.session_id,
-                            }
-                        )
-                    ),
-                    self.loop,
-                )
-                self.logger.bind(tag=TAG).error(
-                    f"tts_priority priority_thread: {text} {e}"
-                )
-
-    def _audio_play_priority_thread(self):
-        while not self.stop_event.is_set():
-            text = None
-            try:
-                try:
-                    audio_datas, text, text_index = self.audio_play_queue.get(timeout=1)
-                except queue.Empty:
-                    if self.stop_event.is_set():
-                        break
-                    continue
-                future = asyncio.run_coroutine_threadsafe(
-                    sendAudioMessage(self, audio_datas, text, text_index), self.loop
-                )
-                future.result()
-            except Exception as e:
-                self.logger.bind(tag=TAG).error(
-                    f"audio_play_priority priority_thread: {text} {e}"
-                )
-
     def _report_worker(self):
         """聊天记录上报工作线程"""
         while not self.stop_event.is_set():
@@ -947,33 +826,9 @@ class ConnectionHandler:
             # 标记任务完成
             self.report_queue.task_done()
 
-    def speak_and_play(self, file_path, content, text_index=0):
-        if file_path is not None:
-            self.logger.bind(tag=TAG).info(f"无需tts转换: 从文件播放，{file_path}")
-            return file_path, content, text_index
-        if content is None or len(content) <= 0:
-            self.logger.bind(tag=TAG).info(f"无需tts转换，query为空，{content}")
-            return None, content, text_index
-        tts_file = self.tts.to_tts(content)
-        if tts_file is None:
-            self.logger.bind(tag=TAG).error(f"tts转换失败，{content}")
-            return None, content, text_index
-        self.logger.bind(tag=TAG).debug(f"TTS 文件生成完毕: {tts_file}")
-        if self.max_output_size > 0:
-            add_device_output(self.headers.get("device-id"), len(content))
-        return tts_file, content, text_index
-
     def clearSpeakStatus(self):
         self.logger.bind(tag=TAG).debug(f"清除服务端讲话状态")
         self.asr_server_receive = True
-        self.tts_last_text_index = -1
-        self.tts_first_text_index = -1
-
-    def recode_first_last_text(self, text, text_index=0):
-        if self.tts_first_text_index == -1:
-            self.logger.bind(tag=TAG).info(f"大模型说出第一句话: {text}")
-            self.tts_first_text_index = text_index
-        self.tts_last_text_index = text_index
 
     async def close(self, ws=None):
         """资源清理方法"""
@@ -1009,23 +864,24 @@ class ConnectionHandler:
 
     def clear_queues(self):
         """清空所有任务队列"""
-        self.logger.bind(tag=TAG).debug(
+        if self.tts:
-            f"开始清理: TTS队列大小={self.tts_queue.qsize()}, 音频队列大小={self.audio_play_queue.qsize()}"
+            self.logger.bind(tag=TAG).debug(
-        )
+                f"开始清理: TTS队列大小={self.tts.tts_text_queue.qsize()}, 音频队列大小={self.tts.tts_audio_queue.qsize()}"
+            )
 
-        # 使用非阻塞方式清空队列
+            # 使用非阻塞方式清空队列
-        for q in [self.tts_queue, self.audio_play_queue]:
+            for q in [self.tts.tts_text_queue, self.tts.tts_audio_queue]:
-            if not q:
+                if not q:
-                continue
+                    continue
-            while True:
+                while True:
-                try:
+                    try:
-                    q.get_nowait()
+                        q.get_nowait()
-                except queue.Empty:
+                    except queue.Empty:
-                    break
+                        break
 
-        self.logger.bind(tag=TAG).debug(
+            self.logger.bind(tag=TAG).debug(
-            f"清理结束: TTS队列大小={self.tts_queue.qsize()}, 音频队列大小={self.audio_play_queue.qsize()}"
+                f"清理结束: TTS队列大小={self.tts.tts_text_queue.qsize()}, 音频队列大小={self.tts.tts_audio_queue.qsize()}"
-        )
+            )
 
     def reset_vad_states(self):
         self.client_audio_buffer = bytearray()

main/xiaozhi-server/core/handle/helloHandle.py

@@ -1,11 +1,13 @@
+import os
+import time
 import json
-from core.handle.sendAudioHandle import send_stt_message
+import random
-from core.utils.util import remove_punctuation_and_length
 import shutil
 import asyncio
-import os
+from core.handle.sendAudioHandle import send_stt_message
-import random
+from core.utils.util import remove_punctuation_and_length
-import time
+from core.providers.tts.dto.dto import ContentType, InterfaceType
+
 
 TAG = __name__
 
@@ -26,7 +28,8 @@ async def handleHelloMessage(conn, msg_json):
         format = audio_params.get("format")
         conn.logger.bind(tag=TAG).info(f"客户端音频格式: {format}")
         conn.audio_format = format
-        conn.asr.set_audio_format(format)
+        if conn.asr is not None:
+            conn.asr.set_audio_format(format)
         conn.welcome_msg["audio_params"] = audio_params
 
     await conn.websocket.send(json.dumps(conn.welcome_msg))
@@ -36,6 +39,10 @@ async def checkWakeupWords(conn, text):
     enable_wakeup_words_response_cache = conn.config[
         "enable_wakeup_words_response_cache"
     ]
+    """是否用的是非流式tts"""
+    if conn.tts and conn.tts.interface_type != InterfaceType.NON_STREAM:
+        return False
+
     """是否开启唤醒词加速"""
     if not enable_wakeup_words_response_cache:
         return False
@@ -43,19 +50,17 @@ async def checkWakeupWords(conn, text):
     _, filtered_text = remove_punctuation_and_length(text)
     if filtered_text in conn.config.get("wakeup_words"):
         await send_stt_message(conn, text)
-        conn.tts_first_text_index = 0
-        conn.tts_last_text_index = 0
-        conn.llm_finish_task = True
 
         file = getWakeupWordFile(WAKEUP_CONFIG["file_name"])
         if file is None:
             asyncio.create_task(wakeupWordsResponse(conn))
             return False
-        opus_packets, _ = conn.tts.audio_to_opus_data(file)
         text_hello = WAKEUP_CONFIG["text"]
         if not text_hello:
             text_hello = text
-        conn.audio_play_queue.put((opus_packets, text_hello, 0))
+        conn.tts.tts_one_sentence(
+            conn, ContentType.FILE, content_file=file, content_detail=text_hello
+        )
         if time.time() - WAKEUP_CONFIG["create_time"] > WAKEUP_CONFIG["refresh_time"]:
             asyncio.create_task(wakeupWordsResponse(conn))
         return True

main/xiaozhi-server/core/handle/intentHandler.py

@@ -4,6 +4,7 @@ import uuid
 from core.handle.sendAudioHandle import send_stt_message
 from core.handle.helloHandle import checkWakeupWords
 from core.utils.util import remove_punctuation_and_length
+from core.providers.tts.dto.dto import ContentType
 from core.utils.dialogue import Message
 from plugins_func.register import Action
 from loguru import logger
@@ -143,11 +144,6 @@ async def process_intent_result(conn, intent_result, original_text):
 
 
 def speak_txt(conn, text):
-    text_index = (
+    conn.tts.tts_one_sentence(conn, ContentType.TEXT, content_detail=text)
-        conn.tts_last_text_index + 1 if hasattr(conn, "tts_last_text_index") else 0
-    )
-    conn.recode_first_last_text(text, text_index)
-    future = conn.executor.submit(conn.speak_and_play, None, text, text_index)
-    conn.llm_finish_task = True
-    conn.tts_queue.put((future, text_index))
     conn.dialogue.put(Message(role="assistant", content=text))
+ 

main/xiaozhi-server/core/handle/receiveAudioHandle.py

@@ -5,6 +5,7 @@ from core.handle.sendAudioHandle import send_stt_message
 from core.handle.intentHandler import handle_user_intent
 from core.utils.output_counter import check_device_output_limit
 from core.handle.reportHandle import enqueue_asr_report
+from core.handle.sendAudioHandle import SentenceType
 from core.utils.util import audio_to_data
 
 TAG = __name__
@@ -46,9 +47,8 @@ async def handleAudioMessage(conn, audio):
             text_len, _ = remove_punctuation_and_length(raw_text)
             if text_len > 0:
                 # 使用自定义模块进行上报
-                enqueue_asr_report(conn, raw_text, copy.deepcopy(conn.asr_audio))
-
                 await startToChat(conn, raw_text)
+                enqueue_asr_report(conn, raw_text, copy.deepcopy(conn.asr_audio))
             else:
                 conn.asr_server_receive = True
         conn.asr_audio.clear()
@@ -110,12 +110,9 @@ async def no_voice_close_connect(conn):
 async def max_out_size(conn):
     text = "不好意思，我现在有点事情要忙，明天这个时候我们再聊，约好了哦！明天不见不散，拜拜！"
     await send_stt_message(conn, text)
-    conn.tts_first_text_index = 0
-    conn.tts_last_text_index = 0
-    conn.llm_finish_task = True
     file_path = "config/assets/max_output_size.wav"
     opus_packets, _ = audio_to_data(file_path)
-    conn.audio_play_queue.put((opus_packets, text, 0))
+    conn.tts.tts_audio_queue.put((SentenceType.LAST, opus_packets, text))
     conn.close_after_chat = True
 
 
@@ -130,14 +127,11 @@ async def check_bind_device(conn):
 
         text = f"请登录控制面板，输入{conn.bind_code}，绑定设备。"
         await send_stt_message(conn, text)
-        conn.tts_first_text_index = 0
-        conn.tts_last_text_index = 6
-        conn.llm_finish_task = True
 
         # 播放提示音
         music_path = "config/assets/bind_code.wav"
         opus_packets, _ = audio_to_data(music_path)
-        conn.audio_play_queue.put((opus_packets, text, 0))
+        conn.tts.tts_audio_queue.put((SentenceType.FIRST, opus_packets, text))
 
         # 逐个播放数字
         for i in range(6):  # 确保只播放6位数字
@@ -145,16 +139,14 @@ async def check_bind_device(conn):
                 digit = conn.bind_code[i]
                 num_path = f"config/assets/bind_code/{digit}.wav"
                 num_packets, _ = audio_to_data(num_path)
-                conn.audio_play_queue.put((num_packets, None, i + 1))
+                conn.tts.tts_audio_queue.put((SentenceType.MIDDLE, num_packets, None))
             except Exception as e:
                 conn.logger.bind(tag=TAG).error(f"播放数字音频失败: {e}")
                 continue
+        conn.tts.tts_audio_queue.put((SentenceType.LAST, [], None))
     else:
         text = f"没有找到该设备的版本信息，请正确配置 OTA地址，然后重新编译固件。"
         await send_stt_message(conn, text)
-        conn.tts_first_text_index = 0
-        conn.tts_last_text_index = 0
-        conn.llm_finish_task = True
         music_path = "config/assets/bind_not_found.wav"
         opus_packets, _ = audio_to_data(music_path)
-        conn.audio_play_queue.put((opus_packets, text, 0))
+        conn.tts.tts_audio_queue.put((SentenceType.LAST, opus_packets, text))

main/xiaozhi-server/core/handle/sendAudioHandle.py

@@ -1,7 +1,9 @@
 import json
 import asyncio
 import time
+from core.providers.tts.dto.dto import SentenceType
 from core.utils.util import get_string_no_punctuation_or_emoji, analyze_emotion
+from loguru import logger
 
 TAG = __name__
 
@@ -30,7 +32,7 @@ emoji_map = {
 }
 
 
-async def sendAudioMessage(conn, audios, text, text_index=0):
+async def sendAudioMessage(conn, sentenceType, audios, text):
     # 发送句子开始消息
     if text is not None:
         emotion = analyze_emotion(text)
@@ -45,18 +47,20 @@ async def sendAudioMessage(conn, audios, text, text_index=0):
                 }
             )
         )
-
+    pre_buffer = False
-    if text_index == conn.tts_first_text_index:
+    if conn.tts.tts_audio_first_sentence and text is not None:
         conn.logger.bind(tag=TAG).info(f"发送第一段语音: {text}")
+        conn.tts.tts_audio_first_sentence = False
+        pre_buffer = True
+
     await send_tts_message(conn, "sentence_start", text)
 
-    is_first_audio = text_index == conn.tts_first_text_index
+    await sendAudio(conn, audios, pre_buffer)
-    await sendAudio(conn, audios, pre_buffer=is_first_audio)
 
     await send_tts_message(conn, "sentence_end", text)
 
     # 发送结束消息（如果是最后一个文本）
-    if conn.llm_finish_task and text_index == conn.tts_last_text_index:
+    if conn.llm_finish_task and sentenceType == SentenceType.LAST:
         await send_tts_message(conn, "stop", None)
         if conn.close_after_chat:
             await conn.close()
@@ -64,6 +68,8 @@ async def sendAudioMessage(conn, audios, text, text_index=0):
 
 # 播放音频
 async def sendAudio(conn, audios, pre_buffer=True):
+    if audios is None or len(audios) == 0:
+        return
     # 流控参数优化
     frame_duration = 60  # 帧时长（毫秒），匹配 Opus 编码
     start_time = time.perf_counter()

main/xiaozhi-server/core/ota_server.py

@@ -98,7 +98,6 @@ class SimpleOtaServer:
                 content_type="application/json",
             )
         except Exception as e:
-            self.logger.bind(tag=TAG).error(f"OTA请求异常: {e}")
             return_json = {"success": False, "message": "request error."}
             response = web.Response(
                 text=json.dumps(return_json, separators=(",", ":")),

main/xiaozhi-server/core/providers/asr/aliyun.py

@@ -155,12 +155,6 @@ class ASRProvider(ASRProviderBase):
         #              f"剩余 {remaining:.2f}秒")
         return time.time() > self.expire_time
 
-    def generate_filename(self, extension=".wav"):
-        return os.path.join(
-            self.output_file,
-            f"tts-{__name__}{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
-        )
-
     def _construct_request_url(self) -> str:
         """构造请求URL，包含参数"""
         request = f"{self.base_url}?appkey={self.app_key}"

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

@@ -1,4 +1,3 @@
-import os
 import uuid
 import json
 import hmac
@@ -8,8 +7,6 @@ import requests
 from datetime import datetime
 from core.providers.tts.base import TTSProviderBase
 
-import http.client
-import urllib.parse
 import time
 import uuid
 from urllib import parse
@@ -163,12 +160,6 @@ class TTSProvider(TTSProviderBase):
         #              f"剩余 {remaining:.2f}秒")
         return time.time() > self.expire_time
 
-    def generate_filename(self, extension=".wav"):
-        return os.path.join(
-            self.output_file,
-            f"tts-{__name__}{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
-        )
-
     async def text_to_speak(self, text, output_file):
         if self._is_token_expired():
             logger.warning("Token已过期，正在自动刷新...")

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

@@ -1,9 +1,27 @@
-import asyncio
-from config.logger import setup_logging
 import os
+import queue
+import uuid
+import asyncio
+import threading
+from core.utils import p3
+from datetime import datetime
+from core.utils import textUtils
 from abc import ABC, abstractmethod
-from core.utils.tts import MarkdownCleaner
+from config.logger import setup_logging
 from core.utils.util import audio_to_data
+from core.utils.tts import MarkdownCleaner
+from core.utils.output_counter import add_device_output
+from core.handle.reportHandle import enqueue_tts_report
+from core.handle.sendAudioHandle import sendAudioMessage
+from core.providers.tts.dto.dto import (
+    TTSMessageDTO,
+    SentenceType,
+    ContentType,
+    InterfaceType,
+)
+
+
+import traceback
 
 TAG = __name__
 logger = setup_logging()
@@ -11,12 +29,51 @@ logger = setup_logging()
 
 class TTSProviderBase(ABC):
     def __init__(self, config, delete_audio_file):
+        self.interface_type = InterfaceType.NON_STREAM
+        self.conn = None
+        self.tts_timeout = 10
         self.delete_audio_file = delete_audio_file
-        self.output_file = config.get("output_dir")
+        self.output_file = config.get("output_dir", "tmp/")
+        self.tts_text_queue = queue.Queue()
+        self.tts_audio_queue = queue.Queue()
+        self.tts_audio_first_sentence = True
 
-    @abstractmethod
+        self.tts_text_buff = []
-    def generate_filename(self):
+        self.punctuations = (
-        pass
+            "。",
+            ".",
+            "？",
+            "?",
+            "！",
+            "!",
+            "；",
+            ";",
+            "：",
+        )
+        self.first_sentence_punctuations = (
+            "，",
+            "~",
+            "、",
+            ",",
+            "。",
+            ".",
+            "？",
+            "?",
+            "！",
+            "!",
+            "；",
+            ";",
+            "：",
+        )
+        self.tts_stop_request = False
+        self.processed_chars = 0
+        self.is_first_sentence = True
+
+    def generate_filename(self, extension=".wav"):
+        return os.path.join(
+            self.output_file,
+            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
+        )
 
     def to_tts(self, text):
         tmp_file = self.generate_filename()
@@ -60,3 +117,224 @@ class TTSProviderBase(ABC):
     def audio_to_opus_data(self, audio_file_path):
         """音频文件转换为Opus编码"""
         return audio_to_data(audio_file_path, is_opus=True)
+
+    def tts_one_sentence(
+        self,
+        conn,
+        content_type,
+        content_detail=None,
+        content_file=None,
+        sentence_id=None,
+    ):
+        """发送一句话"""
+        if not sentence_id:
+            if conn.sentence_id:
+                sentence_id = conn.sentence_id
+            else:
+                sentence_id = str(uuid.uuid4()).replace("-", "")
+                conn.sentence_id = sentence_id
+        self.tts_text_queue.put(
+            TTSMessageDTO(
+                sentence_id=sentence_id,
+                sentence_type=SentenceType.FIRST,
+                content_type=ContentType.ACTION,
+            )
+        )
+        self.tts_text_queue.put(
+            TTSMessageDTO(
+                sentence_id=sentence_id,
+                sentence_type=SentenceType.MIDDLE,
+                content_type=content_type,
+                content_detail=content_detail,
+                content_file=content_file,
+            )
+        )
+        self.tts_text_queue.put(
+            TTSMessageDTO(
+                sentence_id=sentence_id,
+                sentence_type=SentenceType.LAST,
+                content_type=ContentType.ACTION,
+            )
+        )
+
+    async def open_audio_channels(self, conn):
+        self.conn = conn
+        self.tts_timeout = conn.config.get("tts_timeout", 10)
+        # tts 消化线程
+        self.tts_priority_thread = threading.Thread(
+            target=self.tts_text_priority_thread, daemon=True
+        )
+        self.tts_priority_thread.start()
+
+        # 音频播放 消化线程
+        self.audio_play_priority_thread = threading.Thread(
+            target=self._audio_play_priority_thread, daemon=True
+        )
+        self.audio_play_priority_thread.start()
+
+    # 这里默认是非流式的处理方式
+    # 流式处理方式请在子类中重写
+    def tts_text_priority_thread(self):
+        while not self.conn.stop_event.is_set():
+            try:
+                message = self.tts_text_queue.get(timeout=1)
+                if message.sentence_type == SentenceType.FIRST:
+                    # 初始化参数
+                    self.tts_stop_request = False
+                    self.processed_chars = 0
+                    self.tts_text_buff = []
+                    self.is_first_sentence = True
+                    self.tts_audio_first_sentence = True
+                elif ContentType.TEXT == message.content_type:
+                    self.tts_text_buff.append(message.content_detail)
+                    segment_text = self._get_segment_text()
+                    if segment_text:
+                        tts_file = self.to_tts(segment_text)
+                        if tts_file:
+                            audio_datas = self._process_audio_file(tts_file)
+                            self.tts_audio_queue.put(
+                                (message.sentence_type, audio_datas, segment_text)
+                            )
+                elif ContentType.FILE == message.content_type:
+                    self._process_remaining_text()
+                    tts_file = message.content_file
+                    if tts_file and os.path.exists(tts_file):
+                        audio_datas = self._process_audio_file(tts_file)
+                        self.tts_audio_queue.put(
+                            (message.sentence_type, audio_datas, message.content_detail)
+                        )
+
+                if message.sentence_type == SentenceType.LAST:
+                    self._process_remaining_text()
+                    self.tts_audio_queue.put(
+                        (message.sentence_type, [], message.content_detail)
+                    )
+
+            except queue.Empty:
+                continue
+            except Exception as e:
+                logger.bind(tag=TAG).error(
+                    f"处理TTS文本失败: {str(e)}, 类型: {type(e).__name__}, 堆栈: {traceback.format_exc()}"
+                )
+
+    def _audio_play_priority_thread(self):
+        while not self.conn.stop_event.is_set():
+            text = None
+            try:
+                try:
+                    sentence_type, audio_datas, text = self.tts_audio_queue.get(
+                        timeout=1
+                    )
+                except queue.Empty:
+                    if self.conn.stop_event.is_set():
+                        break
+                    continue
+                future = asyncio.run_coroutine_threadsafe(
+                    sendAudioMessage(self.conn, sentence_type, audio_datas, text),
+                    self.conn.loop,
+                )
+                future.result()
+                if self.conn.max_output_size > 0 and text:
+                    add_device_output(self.conn.headers.get("device-id"), len(text))
+                enqueue_tts_report(self.conn, text, audio_datas)
+            except Exception as e:
+                logger.bind(tag=TAG).error(
+                    f"audio_play_priority priority_thread: {text} {e}"
+                )
+
+    async def start_session(self, session_id):
+        pass
+
+    async def finish_session(self, session_id):
+        pass
+
+    async def close(self):
+        """资源清理方法"""
+        if hasattr(self, "ws") and self.ws:
+            await self.ws.close()
+
+    def _get_segment_text(self):
+        # 合并当前全部文本并处理未分割部分
+        full_text = "".join(self.tts_text_buff)
+        current_text = full_text[self.processed_chars :]  # 从未处理的位置开始
+        last_punct_pos = -1
+
+        # 根据是否是第一句话选择不同的标点符号集合
+        punctuations_to_use = (
+            self.first_sentence_punctuations
+            if self.is_first_sentence
+            else self.punctuations
+        )
+
+        for punct in punctuations_to_use:
+            pos = current_text.rfind(punct)
+            if (pos != -1 and last_punct_pos == -1) or (
+                pos != -1 and pos < last_punct_pos
+            ):
+                last_punct_pos = pos
+
+        if last_punct_pos != -1:
+            segment_text_raw = current_text[: last_punct_pos + 1]
+            segment_text = textUtils.get_string_no_punctuation_or_emoji(
+                segment_text_raw
+            )
+            self.processed_chars += len(segment_text_raw)  # 更新已处理字符位置
+
+            # 如果是第一句话，在找到第一个逗号后，将标志设置为False
+            if self.is_first_sentence:
+                self.is_first_sentence = False
+
+            return segment_text
+        elif self.tts_stop_request and current_text:
+            segment_text = current_text
+            self.is_first_sentence = True  # 重置标志
+            return segment_text
+        else:
+            return None
+
+    def _process_audio_file(self, tts_file):
+        """处理音频文件并转换为指定格式
+
+        Args:
+            tts_file: 音频文件路径
+            content_detail: 内容详情
+
+        Returns:
+            tuple: (sentence_type, audio_datas, content_detail)
+        """
+        audio_datas = []
+        if tts_file.endswith(".p3"):
+            audio_datas, _ = p3.decode_opus_from_file(tts_file)
+        elif self.conn.audio_format == "pcm":
+            audio_datas, _ = self.audio_to_pcm_data(tts_file)
+        else:
+            audio_datas, _ = self.audio_to_opus_data(tts_file)
+
+        if (
+            self.delete_audio_file
+            and tts_file is not None
+            and os.path.exists(tts_file)
+            and tts_file.startswith(self.output_file)
+        ):
+            os.remove(tts_file)
+        return audio_datas
+
+    def _process_remaining_text(self):
+        """处理剩余的文本并生成语音
+
+        Returns:
+            bool: 是否成功处理了文本
+        """
+        full_text = "".join(self.tts_text_buff)
+        remaining_text = full_text[self.processed_chars :]
+        if remaining_text:
+            segment_text = textUtils.get_string_no_punctuation_or_emoji(remaining_text)
+            if segment_text:
+                tts_file = self.to_tts(segment_text)
+                audio_datas = self._process_audio_file(tts_file)
+                self.tts_audio_queue.put(
+                    (SentenceType.MIDDLE, audio_datas, segment_text)
+                )
+                self.processed_chars += len(full_text)
+                return True
+        return False

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

@@ -1,9 +1,4 @@
-import os
-import uuid
-import json
-import base64
 import requests
-from datetime import datetime
 from core.providers.tts.base import TTSProviderBase
 
 
@@ -21,12 +16,6 @@ class TTSProvider(TTSProviderBase):
         self.host = "api.coze.cn"
         self.api_url = f"https://{self.host}/v1/audio/speech"
 
-    def generate_filename(self, extension=".wav"):
-        return os.path.join(
-            self.output_file,
-            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
-        )
-
     async def text_to_speak(self, text, output_file):
         request_json = {
             "model": self.model,
@@ -47,4 +36,4 @@ class TTSProvider(TTSProviderBase):
             file_to_save = open(output_file, "wb")
             file_to_save.write(data)
         except Exception as e:
-            raise Exception(f"{__name__} error: {e}")
+            raise Exception(f"{__name__} error: {e}")

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

@@ -0,0 +1,23 @@
+import os
+from config.logger import setup_logging
+from core.providers.tts.base import TTSProviderBase
+
+TAG = __name__
+logger = setup_logging()
+
+
+class DefaultTTS(TTSProviderBase):
+    def __init__(self, config, delete_audio_file=True):
+        super().__init__(config, delete_audio_file)
+        self.output_dir = config.get("output_dir", "output")
+        if not os.path.exists(self.output_dir):
+            os.makedirs(self.output_dir)
+
+    def generate_filename(self):
+        """生成唯一的音频文件名"""
+        import uuid
+
+        return os.path.join(self.output_dir, f"{uuid.uuid4()}.wav")
+
+    async def text_to_speak(self, text, output_file):
+        logger.bind(tag=TAG).error(f"无法实例化 TTS 服务，请检查配置")

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

@@ -1,9 +1,7 @@
-import os
 import uuid
 import json
 import base64
 import requests
-from datetime import datetime
 from core.utils.util import check_model_key
 from core.providers.tts.base import TTSProviderBase
 from config.logger import setup_logging
@@ -41,12 +39,6 @@ class TTSProvider(TTSProviderBase):
         self.header = {"Authorization": f"{self.authorization}{self.access_token}"}
         check_model_key("TTS", self.access_token)
 
-    def generate_filename(self, extension=".wav"):
-        return os.path.join(
-            self.output_file,
-            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
-        )
-
     async def text_to_speak(self, text, output_file):
         request_json = {
             "app": {

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

@@ -0,0 +1,43 @@
+from enum import Enum
+from typing import Union, Optional
+
+
+class SentenceType(Enum):
+    # 说话阶段
+    FIRST = "FIRST"  # 首句话
+    MIDDLE = "MIDDLE"  # 说话中
+    LAST = "LAST"  # 最后一句
+
+
+class ContentType(Enum):
+    # 内容类型
+    TEXT = "TEXT"  # 文本内容
+    FILE = "FILE"  # 文件内容
+    ACTION = "ACTION"  # 动作内容
+
+
+class InterfaceType(Enum):
+    # 接口类型
+    DUAL_STREAM = "DUAL_STREAM"  # 双流式
+    SINGLE_STREAM = "SINGLE_STREAM"  # 单流式
+    NON_STREAM = "NON_STREAM"  # 非流式
+
+
+class TTSMessageDTO:
+    def __init__(
+        self,
+        sentence_id: str,
+        # 说话阶段
+        sentence_type: SentenceType,
+        # 内容类型
+        content_type: ContentType,
+        # 内容详情，一般是需要转换的文本或者音频的歌词
+        content_detail: Optional[str] = None,
+        # 如果内容类型为文件，则需要传入文件路径
+        content_file: Optional[str] = None,
+    ):
+        self.sentence_id = sentence_id
+        self.sentence_type = sentence_type
+        self.content_type = content_type
+        self.content_detail = content_detail
+        self.content_file = content_file

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

@@ -1,12 +1,9 @@
 import base64
-import os
-import uuid
 import requests
 import ormsgpack
 from pathlib import Path
 from pydantic import BaseModel, Field, conint, model_validator
 from typing_extensions import Annotated
-from datetime import datetime
 from typing import Literal
 from core.utils.util import check_model_key, parse_string_to_list
 from core.providers.tts.base import TTSProviderBase
@@ -133,12 +130,6 @@ class TTSProvider(TTSProviderBase):
         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")
 
-    def generate_filename(self, extension=".wav"):
-        return os.path.join(
-            self.output_file,
-            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
-        )
-
     async def text_to_speak(self, text, output_file):
         # Prepare reference data
         byte_audios = [audio_to_bytes(ref_audio) for ref_audio in self.reference_audio]

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

@@ -1,10 +1,5 @@
-import os
-import uuid
-import json
-import base64
 import requests
 from config.logger import setup_logging
-from datetime import datetime
 from core.providers.tts.base import TTSProviderBase
 from core.utils.util import parse_string_to_list
 
@@ -71,12 +66,6 @@ class TTSProvider(TTSProviderBase):
             config.get("aux_ref_audio_paths")
         )
 
-    def generate_filename(self, extension=".wav"):
-        return os.path.join(
-            self.output_file,
-            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
-        )
-
     async def text_to_speak(self, text, output_file):
         request_json = {
             "text": text,

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

@@ -1,8 +1,5 @@
-import os
-import uuid
 import requests
 from config.logger import setup_logging
-from datetime import datetime
 from core.providers.tts.base import TTSProviderBase
 from core.utils.util import parse_string_to_list
 
@@ -36,12 +33,6 @@ class TTSProvider(TTSProviderBase):
         self.inp_refs = parse_string_to_list(config.get("inp_refs"))
         self.if_sr = str(config.get("if_sr", False)).lower() in ("true", "1", "yes")
 
-    def generate_filename(self, extension=".wav"):
-        return os.path.join(
-            self.output_file,
-            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
-        )
-
     async def text_to_speak(self, text, output_file):
         request_params = {
             "refer_wav_path": self.refer_wav_path,
@@ -67,4 +58,3 @@ class TTSProvider(TTSProviderBase):
             error_msg = f"GPT_SoVITS_V3 TTS请求失败: {resp.status_code} - {resp.text}"
             logger.bind(tag=TAG).error(error_msg)
             raise Exception(error_msg)
-

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

@@ -0,0 +1,462 @@
+import os
+import uuid
+import json
+import queue
+import asyncio
+import threading
+import traceback
+import websockets
+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.providers.tts.dto.dto import SentenceType, ContentType, InterfaceType
+
+TAG = __name__
+logger = setup_logging()
+
+PROTOCOL_VERSION = 0b0001
+DEFAULT_HEADER_SIZE = 0b0001
+
+# Message Type:
+FULL_CLIENT_REQUEST = 0b0001
+AUDIO_ONLY_RESPONSE = 0b1011
+FULL_SERVER_RESPONSE = 0b1001
+ERROR_INFORMATION = 0b1111
+
+# Message Type Specific Flags
+MsgTypeFlagNoSeq = 0b0000  # Non-terminal packet with no sequence
+MsgTypeFlagPositiveSeq = 0b1  # Non-terminal packet with sequence > 0
+MsgTypeFlagLastNoSeq = 0b10  # last packet with no sequence
+MsgTypeFlagNegativeSeq = 0b11  # Payload contains event number (int32)
+MsgTypeFlagWithEvent = 0b100
+# Message Serialization
+NO_SERIALIZATION = 0b0000
+JSON = 0b0001
+# Message Compression
+COMPRESSION_NO = 0b0000
+COMPRESSION_GZIP = 0b0001
+
+EVENT_NONE = 0
+EVENT_Start_Connection = 1
+
+EVENT_FinishConnection = 2
+
+EVENT_ConnectionStarted = 50  # 成功建连
+
+EVENT_ConnectionFailed = 51  # 建连失败（可能是无法通过权限认证）
+
+EVENT_ConnectionFinished = 52  # 连接结束
+
+# 上行Session事件
+EVENT_StartSession = 100
+
+EVENT_FinishSession = 102
+# 下行Session事件
+EVENT_SessionStarted = 150
+EVENT_SessionFinished = 152
+
+EVENT_SessionFailed = 153
+
+# 上行通用事件
+EVENT_TaskRequest = 200
+
+# 下行TTS事件
+EVENT_TTSSentenceStart = 350
+
+EVENT_TTSSentenceEnd = 351
+
+EVENT_TTSResponse = 352
+
+
+class Header:
+    def __init__(
+        self,
+        protocol_version=PROTOCOL_VERSION,
+        header_size=DEFAULT_HEADER_SIZE,
+        message_type: int = 0,
+        message_type_specific_flags: int = 0,
+        serial_method: int = NO_SERIALIZATION,
+        compression_type: int = COMPRESSION_NO,
+        reserved_data=0,
+    ):
+        self.header_size = header_size
+        self.protocol_version = protocol_version
+        self.message_type = message_type
+        self.message_type_specific_flags = message_type_specific_flags
+        self.serial_method = serial_method
+        self.compression_type = compression_type
+        self.reserved_data = reserved_data
+
+    def as_bytes(self) -> bytes:
+        return bytes(
+            [
+                (self.protocol_version << 4) | self.header_size,
+                (self.message_type << 4) | self.message_type_specific_flags,
+                (self.serial_method << 4) | self.compression_type,
+                self.reserved_data,
+            ]
+        )
+
+
+class Optional:
+    def __init__(
+        self, event: int = EVENT_NONE, sessionId: str = None, sequence: int = None
+    ):
+        self.event = event
+        self.sessionId = sessionId
+        self.errorCode: int = 0
+        self.connectionId: str | None = None
+        self.response_meta_json: str | None = None
+        self.sequence = sequence
+
+    # 转成 byte 序列
+    def as_bytes(self) -> bytes:
+        option_bytes = bytearray()
+        if self.event != EVENT_NONE:
+            option_bytes.extend(self.event.to_bytes(4, "big", signed=True))
+        if self.sessionId is not None:
+            session_id_bytes = str.encode(self.sessionId)
+            size = len(session_id_bytes).to_bytes(4, "big", signed=True)
+            option_bytes.extend(size)
+            option_bytes.extend(session_id_bytes)
+        if self.sequence is not None:
+            option_bytes.extend(self.sequence.to_bytes(4, "big", signed=True))
+        return option_bytes
+
+
+class Response:
+    def __init__(self, header: Header, optional: Optional):
+        self.optional = optional
+        self.header = header
+        self.payload: bytes | None = None
+
+    def __str__(self):
+        return super().__str__()
+
+
+class TTSProvider(TTSProviderBase):
+    def __init__(self, config, delete_audio_file):
+        super().__init__(config, delete_audio_file)
+        self.interface_type = InterfaceType.DUAL_STREAM
+        self.appId = config.get("appid")
+        self.access_token = config.get("access_token")
+        self.cluster = config.get("cluster")
+        self.resource_id = config.get("resource_id")
+        if config.get("private_voice"):
+            self.speaker = config.get("private_voice")
+        else:
+            self.speaker = config.get("speaker")
+        self.voice = config.get("voice")
+        self.ws_url = config.get("ws_url")
+        self.authorization = config.get("authorization")
+        self.header = {"Authorization": f"{self.authorization}{self.access_token}"}
+        self.enable_two_way = True
+        self.start_connection_flag = False
+        self.tts_text = ""
+        # 合成文字语音后，播放的音频文件列表
+        self.before_stop_play_files = []
+        self.opus_encoder = opus_encoder_utils.OpusEncoderUtils(
+            sample_rate=16000, channels=1, frame_size_ms=60
+        )
+        check_model_key("TTS", self.access_token)
+
+    ###################################################################################
+    # 火山双流式TTS重写父类的方法--开始
+    ###################################################################################
+
+    async def open_audio_channels(self, conn):
+        await super().open_audio_channels(conn)
+        ws_header = {
+            "X-Api-App-Key": self.appId,
+            "X-Api-Access-Key": self.access_token,
+            "X-Api-Resource-Id": self.resource_id,
+            "X-Api-Connect-Id": uuid.uuid4(),
+        }
+        self.ws = await websockets.connect(
+            self.ws_url, additional_headers=ws_header, max_size=1000000000
+        )
+        tts_priority = threading.Thread(
+            target=self._start_monitor_tts_response_thread, daemon=True
+        )
+        tts_priority.start()
+
+    def tts_text_priority_thread(self):
+        while not self.conn.stop_event.is_set():
+            try:
+                message = self.tts_text_queue.get(timeout=1)
+                logger.bind(tag=TAG).debug(
+                    f"TTS任务｜{message.sentence_type.name} ｜ {message.content_type.name}"
+                )
+                if message.sentence_type == SentenceType.FIRST:
+                    # 初始化参数
+                    future = asyncio.run_coroutine_threadsafe(
+                        self.start_session(self.conn.sentence_id), loop=self.conn.loop
+                    )
+                    future.result()
+                    self.tts_audio_first_sentence = True
+                    self.before_stop_play_files.clear()
+                elif ContentType.TEXT == message.content_type:
+                    if message.content_detail:
+                        future = asyncio.run_coroutine_threadsafe(
+                            self.text_to_speak(message.content_detail, None),
+                            loop=self.conn.loop,
+                        )
+                        future.result()
+                elif ContentType.FILE == message.content_type:
+                    self.before_stop_play_files.append(
+                        (message.content_file, message.content_detail)
+                    )
+
+                if message.sentence_type == SentenceType.LAST:
+                    future = asyncio.run_coroutine_threadsafe(
+                        self.finish_session(self.conn.sentence_id), loop=self.conn.loop
+                    )
+                    future.result()
+
+            except queue.Empty:
+                continue
+            except Exception as e:
+                logger.bind(tag=TAG).error(
+                    f"处理TTS文本失败: {str(e)}, 类型: {type(e).__name__}, 堆栈: {traceback.format_exc()}"
+                )
+
+    async def text_to_speak(self, text, _):
+        # 发送文本
+        await self.send_text(self.speaker, text, self.conn.sentence_id)
+        return
+
+    ###################################################################################
+    # 火山双流式TTS重写父类的方法--结束
+    ###################################################################################
+    def _start_monitor_tts_response_thread(self):
+        # 初始化链接
+        asyncio.run_coroutine_threadsafe(
+            self._start_monitor_tts_response(), loop=self.conn.loop
+        )
+
+    async def _start_monitor_tts_response(self):
+        while not self.conn.stop_event.is_set():
+            try:
+                msg = await self.ws.recv()  # 确保 `recv()` 运行在同一个 event loop
+                res = self.parser_response(msg)
+                self.print_response(res, "send_text res:")
+
+                if res.optional.event == EVENT_TTSSentenceStart:
+                    json_data = json.loads(res.payload.decode("utf-8"))
+                    self.tts_text = json_data.get("text", "")
+                    logger.bind(tag=TAG).info(f"语音生成成功: {self.tts_text}")
+                    self.tts_audio_queue.put((SentenceType.FIRST, [], self.tts_text))
+                elif (
+                    res.optional.event == EVENT_TTSResponse
+                    and res.header.message_type == AUDIO_ONLY_RESPONSE
+                ):
+                    logger.bind(tag=TAG).debug(f"推送数据到队列里面～～")
+                    opus_datas = self.wav_to_opus_data_audio_raw(res.payload)
+                    logger.bind(tag=TAG).debug(
+                        f"推送数据到队列里面帧数～～{len(opus_datas)}"
+                    )
+                    self.tts_audio_queue.put((SentenceType.MIDDLE, opus_datas, None))
+                elif res.optional.event == EVENT_TTSSentenceEnd:
+                    logger.bind(tag=TAG).debug(f"句子结束～～{self.tts_text}")
+                elif res.optional.event == EVENT_SessionFinished:
+                    logger.bind(tag=TAG).debug(f"会话结束～～")
+                    for tts_file, text in self.before_stop_play_files:
+                        if tts_file and os.path.exists(tts_file):
+                            audio_datas = self._process_audio_file(tts_file)
+                            self.tts_audio_queue.put(
+                                (SentenceType.MIDDLE, audio_datas, text)
+                            )
+                    self.before_stop_play_files.clear()
+                    self.tts_audio_queue.put((SentenceType.LAST, [], None))
+                    continue
+            except websockets.ConnectionClosed:
+                break  # 连接关闭时退出监听
+            except Exception as e:
+                logger.bind(tag=TAG).error(f"Error in _start_monitor_tts_response: {e}")
+                traceback.print_exc()
+                continue
+
+    async def send_event(
+        self, header: bytes, optional: bytes | None = None, payload: bytes = None
+    ):
+        full_client_request = bytearray(header)
+        if optional is not None:
+            full_client_request.extend(optional)
+        if payload is not None:
+            payload_size = len(payload).to_bytes(4, "big", signed=True)
+            full_client_request.extend(payload_size)
+            full_client_request.extend(payload)
+        await self.ws.send(full_client_request)
+
+    async def send_text(self, speaker: str, text: str, session_id):
+        header = Header(
+            message_type=FULL_CLIENT_REQUEST,
+            message_type_specific_flags=MsgTypeFlagWithEvent,
+            serial_method=JSON,
+        ).as_bytes()
+        optional = Optional(event=EVENT_TaskRequest, sessionId=session_id).as_bytes()
+        payload = self.get_payload_bytes(
+            event=EVENT_TaskRequest, text=text, speaker=speaker
+        )
+        return await self.send_event(header, optional, payload)
+
+    # 读取 res 数组某段 字符串内容
+    def read_res_content(self, res: bytes, offset: int):
+        content_size = int.from_bytes(res[offset : offset + 4], "big", signed=True)
+        offset += 4
+        content = str(res[offset : offset + content_size])
+        offset += content_size
+        return content, offset
+
+    # 读取 payload
+    def read_res_payload(self, res: bytes, offset: int):
+        payload_size = int.from_bytes(res[offset : offset + 4], "big", signed=True)
+        offset += 4
+        payload = res[offset : offset + payload_size]
+        offset += payload_size
+        return payload, offset
+
+    def parser_response(self, res) -> Response:
+        if isinstance(res, str):
+            raise RuntimeError(res)
+        response = Response(Header(), Optional())
+        # 解析结果
+        # header
+        header = response.header
+        num = 0b00001111
+        header.protocol_version = res[0] >> 4 & num
+        header.header_size = res[0] & 0x0F
+        header.message_type = (res[1] >> 4) & num
+        header.message_type_specific_flags = res[1] & 0x0F
+        header.serialization_method = res[2] >> num
+        header.message_compression = res[2] & 0x0F
+        header.reserved = res[3]
+        #
+        offset = 4
+        optional = response.optional
+        if header.message_type == FULL_SERVER_RESPONSE or AUDIO_ONLY_RESPONSE:
+            # read event
+            if header.message_type_specific_flags == MsgTypeFlagWithEvent:
+                optional.event = int.from_bytes(res[offset:8], "big", signed=True)
+                offset += 4
+                if optional.event == EVENT_NONE:
+                    return response
+                # read connectionId
+                elif optional.event == EVENT_ConnectionStarted:
+                    optional.connectionId, offset = self.read_res_content(res, offset)
+                elif optional.event == EVENT_ConnectionFailed:
+                    optional.response_meta_json, offset = self.read_res_content(
+                        res, offset
+                    )
+                elif (
+                    optional.event == EVENT_SessionStarted
+                    or optional.event == EVENT_SessionFailed
+                    or optional.event == EVENT_SessionFinished
+                ):
+                    optional.sessionId, offset = self.read_res_content(res, offset)
+                    optional.response_meta_json, offset = self.read_res_content(
+                        res, offset
+                    )
+                else:
+                    optional.sessionId, offset = self.read_res_content(res, offset)
+                    response.payload, offset = self.read_res_payload(res, offset)
+
+        elif header.message_type == ERROR_INFORMATION:
+            optional.errorCode = int.from_bytes(
+                res[offset : offset + 4], "big", signed=True
+            )
+            offset += 4
+            response.payload, offset = self.read_res_payload(res, offset)
+        return response
+
+    async def start_connection(self):
+        header = Header(
+            message_type=FULL_CLIENT_REQUEST,
+            message_type_specific_flags=MsgTypeFlagWithEvent,
+        ).as_bytes()
+        optional = Optional(event=EVENT_Start_Connection).as_bytes()
+        payload = str.encode("{}")
+        return await self.send_event(header, optional, payload)
+
+    def print_response(self, res, tag_msg: str):
+        logger.bind(tag=TAG).debug(f"===>{tag_msg} header:{res.header.__dict__}")
+        logger.bind(tag=TAG).debug(f"===>{tag_msg} optional:{res.optional.__dict__}")
+
+    def get_payload_bytes(
+        self,
+        uid="1234",
+        event=EVENT_NONE,
+        text="",
+        speaker="",
+        audio_format="pcm",
+        audio_sample_rate=16000,
+    ):
+        return str.encode(
+            json.dumps(
+                {
+                    "user": {"uid": uid},
+                    "event": event,
+                    "namespace": "BidirectionalTTS",
+                    "req_params": {
+                        "text": text,
+                        "speaker": speaker,
+                        "audio_params": {
+                            "format": audio_format,
+                            "sample_rate": audio_sample_rate,
+                        },
+                    },
+                }
+            )
+        )
+
+    async def finish_connection(self):
+        header = Header(
+            message_type=FULL_CLIENT_REQUEST,
+            message_type_specific_flags=MsgTypeFlagWithEvent,
+            serial_method=JSON,
+        ).as_bytes()
+        optional = Optional(event=EVENT_FinishConnection).as_bytes()
+        payload = str.encode("{}")
+        await self.send_event(header, optional, payload)
+        return
+
+    async def start_session(self, session_id):
+        header = Header(
+            message_type=FULL_CLIENT_REQUEST,
+            message_type_specific_flags=MsgTypeFlagWithEvent,
+            serial_method=JSON,
+        ).as_bytes()
+        optional = Optional(event=EVENT_StartSession, sessionId=session_id).as_bytes()
+        payload = self.get_payload_bytes(event=EVENT_StartSession, speaker=self.speaker)
+        await self.send_event(header, optional, payload)
+        logger.bind(tag=TAG).debug(f"开始会话～～{session_id}")
+
+    async def finish_session(self, session_id):
+        logger.bind(tag=TAG).debug(f"关闭会话～～{session_id}")
+        header = Header(
+            message_type=FULL_CLIENT_REQUEST,
+            message_type_specific_flags=MsgTypeFlagWithEvent,
+            serial_method=JSON,
+        ).as_bytes()
+        optional = Optional(event=EVENT_FinishSession, sessionId=session_id).as_bytes()
+        payload = str.encode("{}")
+        await self.send_event(header, optional, payload)
+        return
+
+    async def reset(self):
+        # 关闭之前的对话
+        if self.start_connection_flag:
+            await self.finish_connection()
+            self.start_connection_flag = False
+        await self.start_connection()
+        self.start_connection_flag = True
+
+    async def close(self):
+        """资源清理方法"""
+        await self.finish_connection()
+        await self.ws.close()
+
+    def wav_to_opus_data_audio_raw(self, raw_data_var, is_end=False):
+        opus_datas = self.opus_encoder.encode_pcm_to_opus(raw_data_var, is_end)
+        return opus_datas

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

@@ -1,7 +1,4 @@
-import os
-import uuid
 import requests
-from datetime import datetime
 from core.utils.util import check_model_key
 from core.providers.tts.base import TTSProviderBase
 from config.logger import setup_logging
@@ -29,12 +26,6 @@ class TTSProvider(TTSProviderBase):
         self.output_file = config.get("output_dir", "tmp/")
         check_model_key("TTS", self.api_key)
 
-    def generate_filename(self, extension=".wav"):
-        return os.path.join(
-            self.output_file,
-            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
-        )
-
     async def text_to_speak(self, text, output_file):
         headers = {
             "Authorization": f"Bearer {self.api_key}",

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

@@ -1,7 +1,4 @@
-import os
-import uuid
 import requests
-from datetime import datetime
 from core.providers.tts.base import TTSProviderBase
 
 
@@ -22,12 +19,6 @@ class TTSProvider(TTSProviderBase):
         self.host = "api.siliconflow.cn"
         self.api_url = f"https://{self.host}/v1/audio/speech"
 
-    def generate_filename(self, extension=".wav"):
-        return os.path.join(
-            self.output_file,
-            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
-        )
-
     async def text_to_speak(self, text, output_file):
         request_json = {
             "model": self.model,
@@ -47,4 +38,4 @@ class TTSProvider(TTSProviderBase):
             file_to_save = open(output_file, "wb")
             file_to_save.write(data)
         except Exception as e:
-            raise Exception(f"{__name__} error: {e}")
+            raise Exception(f"{__name__} error: {e}")

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

@@ -1,6 +1,5 @@
 import hashlib
 import hmac
-import os
 import time
 import uuid
 import json
@@ -121,12 +120,6 @@ class TTSProvider(TTSProviderBase):
             msg = msg.encode("utf-8")
         return hmac.new(key, msg, hashlib.sha256).digest()
 
-    def generate_filename(self, extension=".wav"):
-        return os.path.join(
-            self.output_file,
-            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
-        )
-
     async def text_to_speak(self, text, output_file):
         # 构建请求体
         request_json = {

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

@@ -82,4 +82,4 @@ class TTSProvider(TTSProviderBase):
 
         except Exception as e:
             print("error:", e)
-            raise Exception(f"{__name__}: TTS请求失败")
+            raise Exception(f"{__name__}: TTS请求失败")

main/xiaozhi-server/core/utils/opus_encoder_utils.py

@@ -0,0 +1,136 @@
+"""
+Opus编码工具类
+将PCM音频数据编码为Opus格式
+"""
+
+import logging
+import traceback
+
+import numpy as np
+from typing import List, Optional
+from opuslib_next import Encoder
+from opuslib_next import constants
+
+
+class OpusEncoderUtils:
+    """PCM到Opus的编码器"""
+
+    def __init__(self, sample_rate: int, channels: int, frame_size_ms: int):
+        """
+        初始化Opus编码器
+
+        Args:
+            sample_rate: 采样率 (Hz)
+            channels: 通道数 (1=单声道, 2=立体声)
+            frame_size_ms: 帧大小 (毫秒)
+        """
+        self.sample_rate = sample_rate
+        self.channels = channels
+        self.frame_size_ms = frame_size_ms
+        # 计算每帧样本数 = 采样率 * 帧大小(毫秒) / 1000
+        self.frame_size = (sample_rate * frame_size_ms) // 1000
+        # 总帧大小 = 每帧样本数 * 通道数
+        self.total_frame_size = self.frame_size * channels
+
+        # 比特率和复杂度设置
+        self.bitrate = 24000  # bps
+        self.complexity = 10  # 最高质量
+
+        # 缓冲区初始化为空
+        self.buffer = np.array([], dtype=np.int16)
+
+        try:
+            # 创建Opus编码器
+            self.encoder = Encoder(
+                sample_rate, channels, constants.APPLICATION_AUDIO  # 音频优化模式
+            )
+            self.encoder.bitrate = self.bitrate
+            self.encoder.complexity = self.complexity
+            self.encoder.signal = constants.SIGNAL_VOICE  # 语音信号优化
+        except Exception as e:
+            logging.error(f"初始化Opus编码器失败: {e}")
+            raise RuntimeError("初始化失败") from e
+
+    def reset_state(self):
+        """重置编码器状态"""
+        self.encoder.reset_state()
+        self.buffer = np.array([], dtype=np.int16)
+
+    def encode_pcm_to_opus(self, pcm_data: bytes, end_of_stream: bool) -> List[bytes]:
+        """
+        将PCM数据编码为Opus格式
+
+        Args:
+            pcm_data: PCM字节数据
+            end_of_stream: 是否为流的结束
+
+        Returns:
+            Opus数据包列表
+        """
+        # 将字节数据转换为short数组
+        new_samples = self._convert_bytes_to_shorts(pcm_data)
+
+        # 校验PCM数据
+        self._validate_pcm_data(new_samples)
+
+        # 将新数据追加到缓冲区
+        self.buffer = np.append(self.buffer, new_samples)
+
+        opus_packets = []
+        offset = 0
+
+        # 处理所有完整帧
+        while offset <= len(self.buffer) - self.total_frame_size:
+            frame = self.buffer[offset : offset + self.total_frame_size]
+            output = self._encode(frame)
+            if output:
+                opus_packets.append(output)
+            offset += self.total_frame_size
+
+        # 保留未处理的样本
+        self.buffer = self.buffer[offset:]
+
+        # 流结束时处理剩余数据
+        if end_of_stream and len(self.buffer) > 0:
+            # 创建最后一帧并用0填充
+            last_frame = np.zeros(self.total_frame_size, dtype=np.int16)
+            last_frame[: len(self.buffer)] = self.buffer
+
+            output = self._encode(last_frame)
+            if output:
+                opus_packets.append(output)
+            self.buffer = np.array([], dtype=np.int16)
+
+        return opus_packets
+
+    def _encode(self, frame: np.ndarray) -> Optional[bytes]:
+        """编码一帧音频数据"""
+        try:
+            # 将numpy数组转换为bytes
+            frame_bytes = frame.tobytes()
+            # opuslib要求输入字节数必须是channels*2的倍数
+            encoded = self.encoder.encode(frame_bytes, self.frame_size)
+            return encoded
+        except Exception as e:
+            logging.error(f"Opus编码失败: {e}")
+            traceback.print_exc()
+            return None
+
+    def _convert_bytes_to_shorts(self, bytes_data: bytes) -> np.ndarray:
+        """将字节数组转换为short数组 (16位PCM)"""
+        # 假设输入是小端字节序的16位PCM
+        return np.frombuffer(bytes_data, dtype=np.int16)
+
+    def _validate_pcm_data(self, pcm_shorts: np.ndarray) -> None:
+        """验证PCM数据是否有效"""
+        # 16位PCM数据范围是 -32768 到 32767
+        if np.any((pcm_shorts < -32768) | (pcm_shorts > 32767)):
+            invalid_samples = pcm_shorts[(pcm_shorts < -32768) | (pcm_shorts > 32767)]
+            logging.warning(f"发现无效PCM样本: {invalid_samples[:5]}...")
+            # 在实际应用中可以选择裁剪而不是抛出异常
+            # np.clip(pcm_shorts, -32768, 32767, out=pcm_shorts)
+
+    def close(self):
+        """关闭编码器并释放资源"""
+        # opuslib没有明确的关闭方法，Python的垃圾回收会处理
+        pass

main/xiaozhi-server/core/utils/textUtils.py

@@ -0,0 +1,34 @@
+def get_string_no_punctuation_or_emoji(s):
+    """去除字符串首尾的空格、标点符号和表情符号"""
+    chars = list(s)
+    # 处理开头的字符
+    start = 0
+    while start < len(chars) and is_punctuation_or_emoji(chars[start]):
+        start += 1
+    # 处理结尾的字符
+    end = len(chars) - 1
+    while end >= start and is_punctuation_or_emoji(chars[end]):
+        end -= 1
+    return ''.join(chars[start:end + 1])
+
+def is_punctuation_or_emoji(char):
+    """检查字符是否为空格、指定标点或表情符号"""
+    # 定义需要去除的中英文标点（包括全角/半角）
+    punctuation_set = {
+        '，', ',',  # 中文逗号 + 英文逗号
+        '。', '.',  # 中文句号 + 英文句号
+        '！', '!',  # 中文感叹号 + 英文感叹号
+        '-', '－',  # 英文连字符 + 中文全角横线
+        '、'  # 中文顿号
+    }
+    if char.isspace() or char in punctuation_set:
+        return True
+    # 检查表情符号（保留原有逻辑）
+    code_point = ord(char)
+    emoji_ranges = [
+        (0x1F600, 0x1F64F), (0x1F300, 0x1F5FF),
+        (0x1F680, 0x1F6FF), (0x1F900, 0x1F9FF),
+        (0x1FA70, 0x1FAFF), (0x2600, 0x26FF),
+        (0x2700, 0x27BF)
+    ]
+    return any(start <= code_point <= end for start, end in emoji_ranges)

main/xiaozhi-server/core/utils/util.py

@@ -269,16 +269,7 @@ def initialize_modules(
     # 初始化TTS模块
     if init_tts:
         select_tts_module = config["selected_module"]["TTS"]
-        tts_type = (
+        modules["tts"] = initialize_tts(config)
-            select_tts_module
-            if "type" not in config["TTS"][select_tts_module]
-            else config["TTS"][select_tts_module]["type"]
-        )
-        modules["tts"] = tts.create_instance(
-            tts_type,
-            config["TTS"][select_tts_module],
-            str(config.get("delete_audio", True)).lower() in ("true", "1", "yes"),
-        )
         logger.bind(tag=TAG).info(f"初始化组件: tts成功 {select_tts_module}")
 
     # 初始化LLM模块
@@ -355,6 +346,21 @@ def initialize_modules(
     return modules
 
 
+def initialize_tts(config):
+    select_tts_module = config["selected_module"]["TTS"]
+    tts_type = (
+        select_tts_module
+        if "type" not in config["TTS"][select_tts_module]
+        else config["TTS"][select_tts_module]["type"]
+    )
+    new_tts = tts.create_instance(
+        tts_type,
+        config["TTS"][select_tts_module],
+        str(config.get("delete_audio", True)).lower() in ("true", "1", "yes"),
+    )
+    return new_tts
+
+
 def analyze_emotion(text):
     """
     分析文本情感并返回对应的emoji名称（支持中英文）
@@ -882,7 +888,10 @@ def audio_to_data(audio_file_path, is_opus=True):
 
     # 获取原始PCM数据（16位小端）
     raw_data = audio.raw_data
+    return pcm_to_data(raw_data, is_opus), duration
 
+
+def pcm_to_data(raw_data, is_opus=True):
     # 初始化Opus编码器
     encoder = opuslib_next.Encoder(16000, 1, opuslib_next.APPLICATION_AUDIO)
 
@@ -910,7 +919,7 @@ def audio_to_data(audio_file_path, is_opus=True):
 
         datas.append(frame_data)
 
-    return datas, duration
+    return datas
 
 
 def check_vad_update(before_config, new_config):

main/xiaozhi-server/core/websocket_server.py

@@ -19,16 +19,16 @@ class WebSocketServer:
             "VAD" in self.config["selected_module"],
             "ASR" in self.config["selected_module"],
             "LLM" in self.config["selected_module"],
-            "TTS" in self.config["selected_module"],
+            False,
             "Memory" in self.config["selected_module"],
             "Intent" in self.config["selected_module"],
         )
         self._vad = modules["vad"] if "vad" in modules else None
         self._asr = modules["asr"] if "asr" in modules else None
-        self._tts = modules["tts"] if "tts" in modules else None
         self._llm = modules["llm"] if "llm" in modules else None
         self._intent = modules["intent"] if "intent" in modules else None
         self._memory = modules["memory"] if "memory" in modules else None
+
         self.active_connections = set()
 
     async def start(self):
@@ -49,7 +49,6 @@ class WebSocketServer:
             self._vad,
             self._asr,
             self._llm,
-            self._tts,
             self._memory,
             self._intent,
             self,  # 传入server实例
@@ -98,7 +97,7 @@ class WebSocketServer:
                     update_vad,
                     update_asr,
                     "LLM" in new_config["selected_module"],
-                    "TTS" in new_config["selected_module"],
+                    False,
                     "Memory" in new_config["selected_module"],
                     "Intent" in new_config["selected_module"],
                 )
@@ -108,8 +107,6 @@ class WebSocketServer:
                     self._vad = modules["vad"]
                 if "asr" in modules:
                     self._asr = modules["asr"]
-                if "tts" in modules:
-                    self._tts = modules["tts"]
                 if "llm" in modules:
                     self._llm = modules["llm"]
                 if "intent" in modules:

main/xiaozhi-server/plugins_func/functions/play_music.py

@@ -11,6 +11,7 @@ from core.utils import p3
 from core.handle.sendAudioHandle import send_stt_message
 from plugins_func.register import register_function, ToolType, ActionResponse, Action
 from core.utils.dialogue import Message
+from core.providers.tts.dto.dto import TTSMessageDTO, SentenceType, ContentType
 
 TAG = __name__
 
@@ -217,14 +218,36 @@ async def play_local_music(conn, specific_file=None):
         await send_stt_message(conn, text)
         conn.dialogue.put(Message(role="assistant", content=text))
 
-        conn.recode_first_last_text(text, 0)
+        conn.tts.tts_text_queue.put(
-        future = conn.executor.submit(conn.speak_and_play, None, text, 0)
+            TTSMessageDTO(
-        conn.tts_queue.put((future, 0))
+                sentence_id=conn.sentence_id,
-
+                sentence_type=SentenceType.FIRST,
-        conn.recode_first_last_text(text, 1)
+                content_type=ContentType.ACTION,
-        future = conn.executor.submit(conn.speak_and_play, music_path, None, 1)
+            )
-        conn.tts_queue.put((future, 1))
+        )
-        conn.llm_finish_task = True
+        conn.tts.tts_text_queue.put(
+            TTSMessageDTO(
+                sentence_id=conn.sentence_id,
+                sentence_type=SentenceType.MIDDLE,
+                content_type=ContentType.TEXT,
+                content_detail=text,
+            )
+        )
+        conn.tts.tts_text_queue.put(
+            TTSMessageDTO(
+                sentence_id=conn.sentence_id,
+                sentence_type=SentenceType.MIDDLE,
+                content_type=ContentType.FILE,
+                content_file=music_path,
+            )
+        )
+        conn.tts.tts_text_queue.put(
+            TTSMessageDTO(
+                sentence_id=conn.sentence_id,
+                sentence_type=SentenceType.LAST,
+                content_type=ContentType.ACTION,
+            )
+        )
 
     except Exception as e:
         conn.logger.bind(tag=TAG).error(f"播放音乐失败: {str(e)}")