4.7.1-alpha2 (#1153)

Co-authored-by: UUUUnotfound <31206589+UUUUnotfound@users.noreply.github.com> Co-authored-by: Hexiao Zhang <731931282qq@gmail.com> Co-authored-by: heheer <71265218+newfish-cmyk@users.noreply.github.com>
2025-07-26 15:54:11 +00:00 · 2024-04-08 21:17:33 +08:00
parent 3b0b2d68cc
commit 1fbc407ecf
84 changed files with 1773 additions and 715 deletions
--- a/projects/app/package.json
+++ b/projects/app/package.json
@@ -1,6 +1,6 @@
 {
  "name": "app",
-  "version": "4.7",
+  "version": "4.7.1",
  "private": false,
  "scripts": {
    "dev": "next dev",
--- a/projects/app/public/docs/versionIntro.md
+++ b/projects/app/public/docs/versionIntro.md
@@ -1,13 +1,10 @@
 ### FastGPT V4.7

-1. 新增 - 工具调用模块，可以让LLM模型根据用户意图，动态的选择其他模型或插件执行。
-2. 新增 - 分类和内容提取支持 functionCall 模式。部分模型支持 functionCall 不支持 ToolCall，也可以使用了。需要把 LLM 模型配置文件里的 `functionCall` 设置为 `true`， `toolChoice`设置为 `false`。如果 `toolChoice` 为 true，会走 tool 模式。
-3. 新增 - HTTP插件，可实现OpenAPI快速生成插件。
-4. 优化 - 高级编排性能。
-5. 优化 - AI模型选择。
-6. 优化 - 手动输入知识库弹窗。
-7. 优化 - 变量输入弹窗。
-8. 优化 - 浏览器读取文件自动推断编码，减少乱码情况。
-9. [点击查看高级编排介绍文档](https://doc.fastgpt.in/docs/workflow/intro)
-10. [使用文档](https://doc.fastgpt.in/docs/intro/)
-11. [点击查看商业版](https://doc.fastgpt.in/docs/commercial/)
+1. 新增 - 语音输入完整配置。支持选择是否打开语音输入（包括分享页面），支持语音输入后自动发送，支持语音输入后自动语音播放（流式）。
+2. 新增 - Pptx 和 xlsx 文件读取。但所有文件读取都放服务端，会消耗更多的服务器资源，以及无法在上传时预览更多内容。
+3. 新增 - 集成 Laf 云函数，可以读取 Laf 账号中的云函数作为 HTTP 模块。
+4. 修改 - csv导入模板，取消 header 校验，自动获取前两列。
+5. 修复 - 问题补全历史记录BUG
+6. [点击查看高级编排介绍文档](https://doc.fastgpt.in/docs/workflow/intro)
+7. [使用文档](https://doc.fastgpt.in/docs/intro/)
+8. [点击查看商业版](https://doc.fastgpt.in/docs/commercial/)
--- a/projects/app/public/locales/en/common.json
+++ b/projects/app/public/locales/en/common.json
@@ -275,6 +275,7 @@
      "App intro": "App intro",
      "App params config": "App Config",
      "Chat Variable": "",
+      "Config whisper": "Config whisper",
      "External using": "External use",
      "Make a brief introduction of your app": "Make a brief introduction of your app",
      "Max histories": "Dialog round",
@@ -297,6 +298,7 @@
      "Simple Config Tip": "Only basic functions are included. For complex agent functions, use advanced orchestration.",
      "TTS": "Audio Speech",
      "TTS Tip": "After this function is enabled, the voice playback function can be used after each conversation. Use of this feature may incur additional charges.",
+      "TTS start": "Reading content",
      "Team tags": "Team tags",
      "Temperature": "Temperature",
      "Tool call": "Tool call",
@@ -309,6 +311,9 @@
        "This plugin cannot be called as a tool": "This tool cannot be used in easy mode"
      },
      "Welcome Text": "Welcome Text",
+      "Whisper": "Whisper",
+      "Whisper Tip": "",
+      "Whisper config": "Whisper config",
      "create app": "Create App",
      "deterministic": "Deterministic",
      "edit": {
@@ -395,11 +400,23 @@
        "Test Listen": "Test",
        "Test Listen Text": "Hello, this is a voice test, if you can hear this sentence, it means that the voice playback function is normal",
        "Web": "Browser (free)"
+      },
+      "whisper": {
+        "Auto send": "Auto send",
+        "Auto send tip": "After the voice input is completed, you can send it directly, without manually clicking the send button",
+        "Auto tts response": "Auto tts response",
+        "Auto tts response tip": "Questions sent through voice input will be answered directly in the form of voice. Please ensure that the voice broadcast function is enabled.",
+        "Close": "Close",
+        "Not tts tip": "You have not turned on Voice playback and the feature is not available",
+        "Open": "Open",
+        "Switch": "Open whisper"
      }
    },
    "chat": {
      "Admin Mark Content": "Corrected response",
      "Audio Speech Error": "Audio Speech Error",
+      "Cancel Speak": "Cancel speak",
+      "Canceled Speak": "Voice input has been cancelled",
      "Chat API is error or undefined": "The session interface reported an error or returned null",
      "Confirm to clear history": "Confirm to clear history?",
      "Confirm to clear share chat history": " Are you sure to delete all chats?",
@@ -415,6 +432,7 @@
      "Feedback Submit": "Submit",
      "Feedback Success": "Feedback Success",
      "Feedback Update Failed": "Feedback Update Failed",
+      "Finish Speak": "Finish speak",
      "History": "History",
      "History Amount": "{{amount}} records",
      "Mark": "Mark",
--- a/projects/app/public/locales/zh/common.json
+++ b/projects/app/public/locales/zh/common.json
@@ -275,6 +275,7 @@
      "App intro": "应用介绍",
      "App params config": "应用配置",
      "Chat Variable": "对话框变量",
+      "Config whisper": "配置语音输入",
      "External using": "外部使用途径",
      "Make a brief introduction of your app": "给你的 AI 应用一个介绍",
      "Max histories": "聊天记录数量",
@@ -295,8 +296,9 @@
      "Share link desc": "分享链接给其他用户，无需登录即可直接进行使用",
      "Share link desc detail": "可以直接分享该模型给其他用户去进行对话，对方无需登录即可直接进行对话。注意，这个功能会消耗你账号的余额，请保管好链接！",
      "Simple Config Tip": "仅包含基础功能，复杂 agent 功能请使用高级编排。",
-      "TTS": "语音播报",
+      "TTS": "语音播放",
      "TTS Tip": "开启后，每次对话后可使用语音播放功能。使用该功能可能产生额外费用。",
+      "TTS start": "朗读内容",
      "Team tags": "团队标签",
      "Temperature": "温度",
      "Tool call": "工具调用",
@@ -309,6 +311,9 @@
        "This plugin cannot be called as a tool": "该工具无法在简易模式中使用"
      },
      "Welcome Text": "对话开场白",
+      "Whisper": "语音输入",
+      "Whisper Tip": "配置语音输入相关参数",
+      "Whisper config": "语音输入配置",
      "create app": "创建属于你的 AI 应用",
      "deterministic": "严谨",
      "edit": {
@@ -395,11 +400,23 @@
        "Test Listen": "试听",
        "Test Listen Text": "你好，这是语音测试，如果你能听到这句话，说明语音播放功能正常",
        "Web": "浏览器自带(免费)"
+      },
+      "whisper": {
+        "Auto send": "自动发送",
+        "Auto send tip": "语音输入完毕后直接发送，不需要再手动点击发送按键",
+        "Auto tts response": "自动语音回复",
+        "Auto tts response tip": "通过语音输入发送的问题，会直接以语音的形式响应，请确保打开了语音播报功能。",
+        "Close": "关闭",
+        "Not tts tip": "你没有开启语音播放，该功能无法使用",
+        "Open": "开启",
+        "Switch": "开启语音输入"
      }
    },
    "chat": {
      "Admin Mark Content": "纠正后的回复",
      "Audio Speech Error": "语音播报异常",
+      "Cancel Speak": "取消语音输入",
+      "Canceled Speak": "语音输入已取消",
      "Chat API is error or undefined": "对话接口报错或返回为空",
      "Confirm to clear history": "确认清空该应用的在线聊天记录？分享和 API 调用的记录不会被清空。",
      "Confirm to clear share chat history": "确认删除所有聊天记录？",
@@ -415,6 +432,7 @@
      "Feedback Submit": "提交反馈",
      "Feedback Success": "反馈成功!",
      "Feedback Update Failed": "更新反馈状态失败",
+      "Finish Speak": "语音输入完成",
      "History": "记录",
      "History Amount": "{{amount}}条记录",
      "Mark": "标注预期回答",
@@ -1473,7 +1491,7 @@
      "usage": {
        "Ai model": "AI模型",
        "App name": "应用名",
-        "Audio Speech": "语音播报",
+        "Audio Speech": "语音播放",
        "Bill Module": "扣费模块",
        "Chars length": "文本长度",
        "Data Length": "数据长度",
--- a/projects/app/src/components/ChatBox/MessageInput.tsx
+++ b/projects/app/src/components/ChatBox/MessageInput.tsx
@@ -1,7 +1,7 @@
 import { useSpeech } from '@/web/common/hooks/useSpeech';
 import { useSystemStore } from '@/web/common/system/useSystemStore';
 import { Box, Flex, Image, Spinner, Textarea } from '@chakra-ui/react';
-import React, { useRef, useEffect, useCallback, useMemo } from 'react';
+import React, { useRef, useEffect, useCallback, useTransition } from 'react';
 import { useTranslation } from 'next-i18next';
 import MyTooltip from '../MyTooltip';
 import MyIcon from '@fastgpt/web/components/common/Icon';
@@ -12,32 +12,28 @@ import { ChatFileTypeEnum } from '@fastgpt/global/core/chat/constants';
 import { addDays } from 'date-fns';
 import { useRequest } from '@fastgpt/web/hooks/useRequest';
 import { MongoImageTypeEnum } from '@fastgpt/global/common/file/image/constants';
-import { OutLinkChatAuthProps } from '@fastgpt/global/support/permission/chat';
 import { ChatBoxInputFormType, ChatBoxInputType, UserInputFileItemType } from './type';
 import { textareaMinH } from './constants';
 import { UseFormReturn, useFieldArray } from 'react-hook-form';
+import { useChatProviderStore } from './Provider';
 const nanoid = customAlphabet('abcdefghijklmnopqrstuvwxyz1234567890', 6);

 const MessageInput = ({
  onSendMessage,
  onStop,
-  isChatting,
  TextareaDom,
  showFileSelector = false,
  resetInputVal,
-  shareId,
-  outLinkUid,
-  teamId,
-  teamToken,
-  chatForm
-}: OutLinkChatAuthProps & {
-  onSendMessage: (val: ChatBoxInputType) => void;
+  chatForm,
+  appId
+}: {
+  onSendMessage: (val: ChatBoxInputType & { autoTTSResponse?: boolean }) => void;
  onStop: () => void;
-  isChatting: boolean;
  showFileSelector?: boolean;
  TextareaDom: React.MutableRefObject<HTMLTextAreaElement | null>;
  resetInputVal: (val: ChatBoxInputType) => void;
  chatForm: UseFormReturn<ChatBoxInputFormType>;
+  appId?: string;
 }) => {
  const { setValue, watch, control } = chatForm;
  const inputValue = watch('input');
@@ -52,15 +48,8 @@ const MessageInput = ({
    name: 'files'
  });

-  const {
-    isSpeaking,
-    isTransCription,
-    stopSpeak,
-    startSpeak,
-    speakingTimeString,
-    renderAudioGraph,
-    stream
-  } = useSpeech({ shareId, outLinkUid, teamId, teamToken });
+  const { shareId, outLinkUid, teamId, teamToken, isChatting, whisperConfig, autoTTSResponse } =
+    useChatProviderStore();
  const { isPc, whisperModel } = useSystemStore();
  const canvasRef = useRef<HTMLCanvasElement>(null);
  const { t } = useTranslation();
@@ -163,6 +152,16 @@ const MessageInput = ({
    replaceFile([]);
  }, [TextareaDom, fileList, onSendMessage, replaceFile]);

+  /* whisper init */
+  const {
+    isSpeaking,
+    isTransCription,
+    stopSpeak,
+    startSpeak,
+    speakingTimeString,
+    renderAudioGraph,
+    stream
+  } = useSpeech({ appId, shareId, outLinkUid, teamId, teamToken });
  useEffect(() => {
    if (!stream) {
      return;
@@ -180,6 +179,28 @@ const MessageInput = ({
    };
    renderCurve();
  }, [renderAudioGraph, stream]);
+  const finishWhisperTranscription = useCallback(
+    (text: string) => {
+      if (!text) return;
+      if (whisperConfig?.autoSend) {
+        onSendMessage({
+          text,
+          files: fileList,
+          autoTTSResponse
+        });
+        replaceFile([]);
+      } else {
+        resetInputVal({ text });
+      }
+    },
+    [autoTTSResponse, fileList, onSendMessage, replaceFile, resetInputVal, whisperConfig?.autoSend]
+  );
+  const onWhisperRecord = useCallback(() => {
+    if (isSpeaking) {
+      return stopSpeak();
+    }
+    startSpeak(finishWhisperTranscription);
+  }, [finishWhisperTranscription, isSpeaking, startSpeak, stopSpeak]);

  return (
    <Box m={['0 auto', '10px auto']} w={'100%'} maxW={['auto', 'min(800px, 100%)']} px={[0, 5]}>
@@ -369,7 +390,7 @@ const MessageInput = ({
            bottom={['10px', '12px']}
          >
            {/* voice-input */}
-            {!shareId && !havInput && !isChatting && !!whisperModel && (
+            {whisperConfig.open && !havInput && !isChatting && !!whisperModel && (
              <>
                <canvas
                  ref={canvasRef}
@@ -380,32 +401,49 @@ const MessageInput = ({
                    zIndex: 0
                  }}
                />
-                <Flex
-                  mr={2}
-                  alignItems={'center'}
-                  justifyContent={'center'}
-                  flexShrink={0}
-                  h={['26px', '32px']}
-                  w={['26px', '32px']}
-                  borderRadius={'md'}
-                  cursor={'pointer'}
-                  _hover={{ bg: '#F5F5F8' }}
-                  onClick={() => {
-                    if (isSpeaking) {
-                      return stopSpeak();
-                    }
-                    startSpeak((text) => resetInputVal({ text }));
-                  }}
-                >
-                  <MyTooltip label={isSpeaking ? t('core.chat.Stop Speak') : t('core.chat.Record')}>
+                {isSpeaking && (
+                  <MyTooltip label={t('core.chat.Cancel Speak')}>
+                    <Flex
+                      mr={2}
+                      alignItems={'center'}
+                      justifyContent={'center'}
+                      flexShrink={0}
+                      h={['26px', '32px']}
+                      w={['26px', '32px']}
+                      borderRadius={'md'}
+                      cursor={'pointer'}
+                      _hover={{ bg: '#F5F5F8' }}
+                      onClick={() => stopSpeak(true)}
+                    >
+                      <MyIcon
+                        name={'core/chat/cancelSpeak'}
+                        width={['20px', '22px']}
+                        height={['20px', '22px']}
+                      />
+                    </Flex>
+                  </MyTooltip>
+                )}
+                <MyTooltip label={isSpeaking ? t('core.chat.Finish Speak') : t('core.chat.Record')}>
+                  <Flex
+                    mr={2}
+                    alignItems={'center'}
+                    justifyContent={'center'}
+                    flexShrink={0}
+                    h={['26px', '32px']}
+                    w={['26px', '32px']}
+                    borderRadius={'md'}
+                    cursor={'pointer'}
+                    _hover={{ bg: '#F5F5F8' }}
+                    onClick={onWhisperRecord}
+                  >
                    <MyIcon
-                      name={isSpeaking ? 'core/chat/stopSpeechFill' : 'core/chat/recordFill'}
+                      name={isSpeaking ? 'core/chat/finishSpeak' : 'core/chat/recordFill'}
                      width={['20px', '22px']}
                      height={['20px', '22px']}
                      color={isSpeaking ? 'primary.500' : 'myGray.600'}
                    />
-                  </MyTooltip>
-                </Flex>
+                  </Flex>
+                </MyTooltip>
              </>
            )}
            {/* send and stop icon */}
--- a/projects/app/src/components/ChatBox/Provider.tsx
+++ b/projects/app/src/components/ChatBox/Provider.tsx
@@ -0,0 +1,176 @@
+import React, { useContext, createContext, useState, useMemo, useEffect, useCallback } from 'react';
+import { useAudioPlay } from '@/web/common/utils/voice';
+import { OutLinkChatAuthProps } from '@fastgpt/global/support/permission/chat';
+import { ModuleItemType } from '@fastgpt/global/core/module/type';
+import { splitGuideModule } from '@fastgpt/global/core/module/utils';
+import {
+  AppTTSConfigType,
+  AppWhisperConfigType,
+  VariableItemType
+} from '@fastgpt/global/core/app/type';
+import { ChatSiteItemType } from '@fastgpt/global/core/chat/type';
+
+type useChatStoreType = OutLinkChatAuthProps & {
+  welcomeText: string;
+  variableModules: VariableItemType[];
+  questionGuide: boolean;
+  ttsConfig: AppTTSConfigType;
+  whisperConfig: AppWhisperConfigType;
+  autoTTSResponse: boolean;
+  startSegmentedAudio: () => Promise<any>;
+  splitText2Audio: (text: string, done?: boolean | undefined) => void;
+  finishSegmentedAudio: () => void;
+  audioLoading: boolean;
+  audioPlaying: boolean;
+  hasAudio: boolean;
+  playAudioByText: ({
+    text,
+    buffer
+  }: {
+    text: string;
+    buffer?: Uint8Array | undefined;
+  }) => Promise<{
+    buffer?: Uint8Array | undefined;
+  }>;
+  cancelAudio: () => void;
+  audioPlayingChatId: string | undefined;
+  setAudioPlayingChatId: React.Dispatch<React.SetStateAction<string | undefined>>;
+  chatHistories: ChatSiteItemType[];
+  setChatHistories: React.Dispatch<React.SetStateAction<ChatSiteItemType[]>>;
+  isChatting: boolean;
+};
+const StateContext = createContext<useChatStoreType>({
+  welcomeText: '',
+  variableModules: [],
+  questionGuide: false,
+  ttsConfig: {
+    type: 'none',
+    model: undefined,
+    voice: undefined,
+    speed: undefined
+  },
+  whisperConfig: {
+    open: false,
+    autoSend: false,
+    autoTTSResponse: false
+  },
+  autoTTSResponse: false,
+  startSegmentedAudio: function (): Promise<any> {
+    throw new Error('Function not implemented.');
+  },
+  splitText2Audio: function (text: string, done?: boolean | undefined): void {
+    throw new Error('Function not implemented.');
+  },
+  chatHistories: [],
+  setChatHistories: function (value: React.SetStateAction<ChatSiteItemType[]>): void {
+    throw new Error('Function not implemented.');
+  },
+  isChatting: false,
+  audioLoading: false,
+  audioPlaying: false,
+  hasAudio: false,
+  playAudioByText: function ({
+    text,
+    buffer
+  }: {
+    text: string;
+    buffer?: Uint8Array | undefined;
+  }): Promise<{ buffer?: Uint8Array | undefined }> {
+    throw new Error('Function not implemented.');
+  },
+  cancelAudio: function (): void {
+    throw new Error('Function not implemented.');
+  },
+  audioPlayingChatId: undefined,
+  setAudioPlayingChatId: function (value: React.SetStateAction<string | undefined>): void {
+    throw new Error('Function not implemented.');
+  },
+  finishSegmentedAudio: function (): void {
+    throw new Error('Function not implemented.');
+  }
+});
+
+export type ChatProviderProps = OutLinkChatAuthProps & {
+  userGuideModule?: ModuleItemType;
+
+  // not chat test params
+  chatId?: string;
+  children: React.ReactNode;
+};
+
+export const useChatProviderStore = () => useContext(StateContext);
+
+const Provider = ({
+  shareId,
+  outLinkUid,
+  teamId,
+  teamToken,
+  userGuideModule,
+  children
+}: ChatProviderProps) => {
+  const [chatHistories, setChatHistories] = useState<ChatSiteItemType[]>([]);
+
+  const { welcomeText, variableModules, questionGuide, ttsConfig, whisperConfig } = useMemo(
+    () => splitGuideModule(userGuideModule),
+    [userGuideModule]
+  );
+
+  // segment audio
+  const [audioPlayingChatId, setAudioPlayingChatId] = useState<string>();
+  const {
+    audioLoading,
+    audioPlaying,
+    hasAudio,
+    playAudioByText,
+    cancelAudio,
+    startSegmentedAudio,
+    finishSegmentedAudio,
+    splitText2Audio
+  } = useAudioPlay({
+    ttsConfig,
+    shareId,
+    outLinkUid,
+    teamId,
+    teamToken
+  });
+
+  const autoTTSResponse =
+    whisperConfig?.open && whisperConfig?.autoSend && whisperConfig?.autoTTSResponse && hasAudio;
+
+  const isChatting = useMemo(
+    () =>
+      chatHistories[chatHistories.length - 1] &&
+      chatHistories[chatHistories.length - 1]?.status !== 'finish',
+    [chatHistories]
+  );
+
+  const value: useChatStoreType = {
+    shareId,
+    outLinkUid,
+    teamId,
+    teamToken,
+    welcomeText,
+    variableModules,
+    questionGuide,
+    ttsConfig,
+    whisperConfig,
+    autoTTSResponse,
+    startSegmentedAudio,
+    finishSegmentedAudio,
+    splitText2Audio,
+    audioLoading,
+    audioPlaying,
+    hasAudio,
+    playAudioByText,
+    cancelAudio,
+    audioPlayingChatId,
+    setAudioPlayingChatId,
+    chatHistories,
+    setChatHistories,
+    isChatting
+  };
+
+  return <StateContext.Provider value={value}>{children}</StateContext.Provider>;
+};
+
+export default React.memo(Provider);
--- a/projects/app/src/components/ChatBox/components/ChatController.tsx
+++ b/projects/app/src/components/ChatBox/components/ChatController.tsx
@@ -2,21 +2,18 @@ import { useCopyData } from '@/web/common/hooks/useCopyData';
 import { useAudioPlay } from '@/web/common/utils/voice';
 import { Flex, FlexProps, Image, css, useTheme } from '@chakra-ui/react';
 import { ChatSiteItemType } from '@fastgpt/global/core/chat/type';
-import { AppTTSConfigType } from '@fastgpt/global/core/module/type';
-import { OutLinkChatAuthProps } from '@fastgpt/global/support/permission/chat';
 import MyTooltip from '@fastgpt/web/components/common/MyTooltip';
-import React from 'react';
+import React, { useMemo } from 'react';
 import { useTranslation } from 'next-i18next';
 import MyIcon from '@fastgpt/web/components/common/Icon';
 import { formatChatValue2InputType } from '../utils';
 import { ChatRoleEnum } from '@fastgpt/global/core/chat/constants';
+import { useChatProviderStore } from '../Provider';

 export type ChatControllerProps = {
-  isChatting: boolean;
+  isLastChild: boolean;
  chat: ChatSiteItemType;
-  setChatHistories?: React.Dispatch<React.SetStateAction<ChatSiteItemType[]>>;
  showVoiceIcon?: boolean;
-  ttsConfig?: AppTTSConfigType;
  onRetry?: () => void;
  onDelete?: () => void;
  onMark?: () => void;
@@ -27,33 +24,29 @@ export type ChatControllerProps = {
 };

 const ChatController = ({
-  isChatting,
  chat,
-  setChatHistories,
+  isLastChild,
  showVoiceIcon,
-  ttsConfig,
  onReadUserDislike,
  onCloseUserLike,
  onMark,
  onRetry,
  onDelete,
  onAddUserDislike,
-  onAddUserLike,
-  shareId,
-  outLinkUid,
-  teamId,
-  teamToken
-}: OutLinkChatAuthProps & ChatControllerProps & FlexProps) => {
+  onAddUserLike
+}: ChatControllerProps & FlexProps) => {
  const theme = useTheme();
-  const { t } = useTranslation();
-  const { copyData } = useCopyData();
-  const { audioLoading, audioPlaying, hasAudio, playAudio, cancelAudio } = useAudioPlay({
-    ttsConfig,
-    shareId,
-    outLinkUid,
-    teamId,
-    teamToken
-  });
+  const {
+    isChatting,
+    setChatHistories,
+    audioLoading,
+    audioPlaying,
+    hasAudio,
+    playAudioByText,
+    cancelAudio,
+    audioPlayingChatId,
+    setAudioPlayingChatId
+  } = useChatProviderStore();
  const controlIconStyle = {
    w: '14px',
    cursor: 'pointer',
@@ -67,6 +60,11 @@ const ChatController = ({
    display: 'flex'
  };

+  const { t } = useTranslation();
+  const { copyData } = useCopyData();
+
+  const chatText = useMemo(() => formatChatValue2InputType(chat.value).text || '', [chat.value]);
+
  return (
    <Flex
      {...controlContainerStyle}
@@ -86,7 +84,7 @@ const ChatController = ({
          {...controlIconStyle}
          name={'copy'}
          _hover={{ color: 'primary.600' }}
-          onClick={() => copyData(formatChatValue2InputType(chat.value).text || '')}
+          onClick={() => copyData(chatText)}
        />
      </MyTooltip>
      {!!onDelete && !isChatting && (
@@ -113,51 +111,65 @@ const ChatController = ({
      )}
      {showVoiceIcon &&
        hasAudio &&
-        (audioLoading ? (
-          <MyTooltip label={t('common.Loading')}>
-            <MyIcon {...controlIconStyle} name={'common/loading'} />
-          </MyTooltip>
-        ) : audioPlaying ? (
-          <Flex alignItems={'center'}>
-            <MyTooltip label={t('core.chat.tts.Stop Speech')}>
+        (() => {
+          const isPlayingChat = chat.dataId === audioPlayingChatId;
+          if (isPlayingChat && audioPlaying) {
+            return (
+              <Flex alignItems={'center'}>
+                <MyTooltip label={t('core.chat.tts.Stop Speech')}>
+                  <MyIcon
+                    {...controlIconStyle}
+                    borderRight={'none'}
+                    name={'core/chat/stopSpeech'}
+                    color={'#E74694'}
+                    onClick={cancelAudio}
+                  />
+                </MyTooltip>
+                <Image
+                  src="/icon/speaking.gif"
+                  w={'23px'}
+                  alt={''}
+                  borderRight={theme.borders.base}
+                />
+              </Flex>
+            );
+          }
+          if (isPlayingChat && audioLoading) {
+            return (
+              <MyTooltip label={t('common.Loading')}>
+                <MyIcon {...controlIconStyle} name={'common/loading'} />
+              </MyTooltip>
+            );
+          }
+          return (
+            <MyTooltip label={t('core.app.TTS start')}>
              <MyIcon
                {...controlIconStyle}
-                borderRight={'none'}
-                name={'core/chat/stopSpeech'}
-                color={'#E74694'}
-                onClick={() => cancelAudio()}
+                name={'common/voiceLight'}
+                _hover={{ color: '#E74694' }}
+                onClick={async () => {
+                  setAudioPlayingChatId(chat.dataId);
+                  const response = await playAudioByText({
+                    buffer: chat.ttsBuffer,
+                    text: chatText
+                  });
+
+                  if (!setChatHistories || !response.buffer) return;
+                  setChatHistories((state) =>
+                    state.map((item) =>
+                      item.dataId === chat.dataId
+                        ? {
+                            ...item,
+                            ttsBuffer: response.buffer
+                          }
+                        : item
+                    )
+                  );
+                }}
              />
            </MyTooltip>
-            <Image src="/icon/speaking.gif" w={'23px'} alt={''} borderRight={theme.borders.base} />
-          </Flex>
-        ) : (
-          <MyTooltip label={t('core.app.TTS')}>
-            <MyIcon
-              {...controlIconStyle}
-              name={'common/voiceLight'}
-              _hover={{ color: '#E74694' }}
-              onClick={async () => {
-                const response = await playAudio({
-                  buffer: chat.ttsBuffer,
-                  chatItemId: chat.dataId,
-                  text: formatChatValue2InputType(chat.value).text || ''
-                });
-
-                if (!setChatHistories || !response.buffer) return;
-                setChatHistories((state) =>
-                  state.map((item) =>
-                    item.dataId === chat.dataId
-                      ? {
-                          ...item,
-                          ttsBuffer: response.buffer
-                        }
-                      : item
-                  )
-                );
-              }}
-            />
-          </MyTooltip>
-        ))}
+          );
+        })()}
      {!!onMark && (
        <MyTooltip label={t('core.chat.Mark')}>
          <MyIcon
--- a/projects/app/src/components/ChatBox/components/ChatItem.tsx
+++ b/projects/app/src/components/ChatBox/components/ChatItem.tsx
@@ -25,6 +25,7 @@ import {
  ChatStatusEnum
 } from '@fastgpt/global/core/chat/constants';
 import FilesBlock from './FilesBox';
+import { useChatProviderStore } from '../Provider';

 const colorMap = {
  [ChatStatusEnum.loading]: {
@@ -56,11 +57,9 @@ const ChatItem = ({
    status: `${ChatStatusEnum}`;
    name: string;
  };
-  isLastChild?: boolean;
  questionGuides?: string[];
  children?: React.ReactNode;
 } & ChatControllerProps) => {
-  const theme = useTheme();
  const styleMap: BoxProps =
    type === ChatRoleEnum.Human
      ? {
@@ -77,7 +76,9 @@ const ChatItem = ({
          textAlign: 'left',
          bg: 'myGray.50'
        };
-  const { chat, isChatting } = chatControllerProps;
+
+  const { isChatting } = useChatProviderStore();
+  const { chat } = chatControllerProps;

  const ContentCard = useMemo(() => {
    if (type === 'Human') {
@@ -209,7 +210,7 @@ ${toolResponse}`}
      <Flex w={'100%'} alignItems={'center'} gap={2} justifyContent={styleMap.justifyContent}>
        {isChatting && type === ChatRoleEnum.AI && isLastChild ? null : (
          <Box order={styleMap.order} ml={styleMap.ml}>
-            <ChatController {...chatControllerProps} />
+            <ChatController {...chatControllerProps} isLastChild={isLastChild} />
          </Box>
        )}
        <ChatAvatar src={avatar} type={type} />
--- a/projects/app/src/components/ChatBox/components/VariableInput.tsx
+++ b/projects/app/src/components/ChatBox/components/VariableInput.tsx
@@ -1,4 +1,4 @@
-import { VariableItemType } from '@fastgpt/global/core/module/type';
+import { VariableItemType } from '@fastgpt/global/core/app/type.d';
 import React, { useState } from 'react';
 import { UseFormReturn } from 'react-hook-form';
 import { useTranslation } from 'next-i18next';
--- a/projects/app/src/components/ChatBox/constants.ts
+++ b/projects/app/src/components/ChatBox/constants.ts
@@ -11,3 +11,9 @@ export const MessageCardStyle: BoxProps = {
  maxW: ['calc(100% - 25px)', 'calc(100% - 40px)'],
  color: 'myGray.900'
 };
+
+export enum FeedbackTypeEnum {
+  user = 'user',
+  admin = 'admin',
+  hidden = 'hidden'
+}
--- a/projects/app/src/components/ChatBox/index.tsx
+++ b/projects/app/src/components/ChatBox/index.tsx
@@ -11,7 +11,6 @@ import React, {
 import Script from 'next/script';
 import { throttle } from 'lodash';
 import type {
-  AIChatItemType,
  AIChatItemValueItemType,
  ChatSiteItemType,
  UserChatItemValueItemType
@@ -39,7 +38,6 @@ import type { AdminMarkType } from './SelectMarkCollection';
 import MyTooltip from '../MyTooltip';

 import { postQuestionGuide } from '@/web/core/ai/api';
-import { splitGuideModule } from '@fastgpt/global/core/module/utils';
 import type {
  generatingMessageProps,
  StartChatFnProps,
@@ -55,6 +53,8 @@ import { ChatItemValueTypeEnum, ChatRoleEnum } from '@fastgpt/global/core/chat/c
 import { formatChatValue2InputType } from './utils';
 import { textareaMinH } from './constants';
 import { SseResponseEventEnum } from '@fastgpt/global/core/module/runtime/constants';
+import ChatProvider, { useChatProviderStore } from './Provider';
+
 import ChatItem from './components/ChatItem';

 import dynamic from 'next/dynamic';
@@ -82,9 +82,9 @@ type Props = OutLinkChatAuthProps & {
  userGuideModule?: ModuleItemType;
  showFileSelector?: boolean;
  active?: boolean; // can use
+  appId: string;

  // not chat test params
-  appId?: string;
  chatId?: string;

  onUpdateVariable?: (e: Record<string, any>) => void;
@@ -112,7 +112,6 @@ const ChatBox = (
    showEmptyIntro = false,
    appAvatar,
    userAvatar,
-    userGuideModule,
    showFileSelector,
    active = true,
    appId,
@@ -137,7 +136,6 @@ const ChatBox = (
  const questionGuideController = useRef(new AbortController());
  const isNewChatReplace = useRef(false);

-  const [chatHistories, setChatHistories] = useState<ChatSiteItemType[]>([]);
  const [feedbackId, setFeedbackId] = useState<string>();
  const [readFeedbackData, setReadFeedbackData] = useState<{
    chatItemId: string;
@@ -146,17 +144,20 @@ const ChatBox = (
  const [adminMarkData, setAdminMarkData] = useState<AdminMarkType & { chatItemId: string }>();
  const [questionGuides, setQuestionGuide] = useState<string[]>([]);

-  const isChatting = useMemo(
-    () =>
-      chatHistories[chatHistories.length - 1] &&
-      chatHistories[chatHistories.length - 1]?.status !== 'finish',
-    [chatHistories]
-  );
+  const {
+    welcomeText,
+    variableModules,
+    questionGuide,
+    startSegmentedAudio,
+    finishSegmentedAudio,
+    setAudioPlayingChatId,
+    splitText2Audio,
+    chatHistories,
+    setChatHistories,
+    isChatting
+  } = useChatProviderStore();

-  const { welcomeText, variableModules, questionGuide, ttsConfig } = useMemo(
-    () => splitGuideModule(userGuideModule),
-    [userGuideModule]
-  );
+  /* variable */
  const filterVariableModules = useMemo(
    () => variableModules.filter((item) => item.type !== VariableInputEnum.external),
    [variableModules]
@@ -171,10 +172,9 @@ const ChatBox = (
      chatStarted: false
    }
  });
-  const { setValue, watch, handleSubmit, control } = chatForm;
+  const { setValue, watch, handleSubmit } = chatForm;
  const variables = watch('variables');
  const chatStarted = watch('chatStarted');
-
  const variableIsFinish = useMemo(() => {
    if (!filterVariableModules || filterVariableModules.length === 0 || chatHistories.length > 0)
      return true;
@@ -212,12 +212,21 @@ const ChatBox = (
  );
  // eslint-disable-next-line react-hooks/exhaustive-deps
  const generatingMessage = useCallback(
-    ({ event, text = '', status, name, tool }: generatingMessageProps) => {
+    ({
+      event,
+      text = '',
+      status,
+      name,
+      tool,
+      autoTTSResponse
+    }: generatingMessageProps & { autoTTSResponse?: boolean }) => {
      setChatHistories((state) =>
        state.map((item, index) => {
          if (index !== state.length - 1) return item;
          if (item.obj !== ChatRoleEnum.AI) return item;

+          autoTTSResponse && splitText2Audio(formatChatValue2InputType(item.value).text || '');
+
          const lastValue: AIChatItemValueItemType = JSON.parse(
            JSON.stringify(item.value[item.value.length - 1])
          );
@@ -299,7 +308,7 @@ const ChatBox = (
      );
      generatingScroll();
    },
-    [generatingScroll]
+    [generatingScroll, setChatHistories, splitText2Audio]
  );

  // 重置输入内容
@@ -357,8 +366,10 @@ const ChatBox = (
    ({
      text = '',
      files = [],
-      history = chatHistories
+      history = chatHistories,
+      autoTTSResponse = false
    }: ChatBoxInputType & {
+      autoTTSResponse?: boolean;
      history?: ChatSiteItemType[];
    }) => {
      handleSubmit(async ({ variables }) => {
@@ -370,7 +381,7 @@ const ChatBox = (
          });
          return;
        }
-        questionGuideController.current?.abort('stop');
+
        text = text.trim();

        if (!text && files.length === 0) {
@@ -381,6 +392,15 @@ const ChatBox = (
          return;
        }

+        const responseChatId = getNanoid(24);
+        questionGuideController.current?.abort('stop');
+
+        // set auto audio playing
+        if (autoTTSResponse) {
+          await startSegmentedAudio();
+          setAudioPlayingChatId(responseChatId);
+        }
+
        const newChatList: ChatSiteItemType[] = [
          ...history,
          {
@@ -409,7 +429,7 @@ const ChatBox = (
            status: 'finish'
          },
          {
-            dataId: getNanoid(24),
+            dataId: responseChatId,
            obj: ChatRoleEnum.AI,
            value: [
              {
@@ -447,7 +467,7 @@ const ChatBox = (
            chatList: newChatList,
            messages,
            controller: abortSignal,
-            generatingMessage,
+            generatingMessage: (e) => generatingMessage({ ...e, autoTTSResponse }),
            variables
          });

@@ -485,6 +505,9 @@ const ChatBox = (
            generatingScroll();
            isPc && TextareaDom.current?.focus();
          }, 100);
+
+          // tts audio
+          autoTTSResponse && splitText2Audio(responseText, true);
        } catch (err: any) {
          toast({
            title: t(getErrText(err, 'core.chat.error.Chat error')),
@@ -509,11 +532,14 @@ const ChatBox = (
            })
          );
        }
+
+        autoTTSResponse && finishSegmentedAudio();
      })();
    },
    [
      chatHistories,
      createQuestionGuide,
+      finishSegmentedAudio,
      generatingMessage,
      generatingScroll,
      handleSubmit,
@@ -521,6 +547,10 @@ const ChatBox = (
      isPc,
      onStartChat,
      resetInputVal,
+      setAudioPlayingChatId,
+      setChatHistories,
+      splitText2Audio,
+      startSegmentedAudio,
      t,
      toast
    ]
@@ -875,9 +905,9 @@ const ChatBox = (
                    type={item.obj}
                    avatar={item.obj === 'Human' ? userAvatar : appAvatar}
                    chat={item}
-                    isChatting={isChatting}
                    onRetry={retryInput(item.dataId)}
                    onDelete={delOneMessage(item.dataId)}
+                    isLastChild={index === chatHistories.length - 1}
                  />
                )}
                {item.obj === 'AI' && (
@@ -886,17 +916,14 @@ const ChatBox = (
                      type={item.obj}
                      avatar={appAvatar}
                      chat={item}
-                      isChatting={isChatting}
+                      isLastChild={index === chatHistories.length - 1}
                      {...(item.obj === 'AI' && {
-                        setChatHistories,
                        showVoiceIcon,
-                        ttsConfig,
                        shareId,
                        outLinkUid,
                        teamId,
                        teamToken,
                        statusBoxData,
-                        isLastChild: index === chatHistories.length - 1,
                        questionGuides,
                        onMark: onMark(
                          item,
@@ -957,15 +984,11 @@ const ChatBox = (
        <MessageInput
          onSendMessage={sendPrompt}
          onStop={() => chatController.current?.abort('stop')}
-          isChatting={isChatting}
          TextareaDom={TextareaDom}
          resetInputVal={resetInputVal}
          showFileSelector={showFileSelector}
-          shareId={shareId}
-          outLinkUid={outLinkUid}
-          teamId={teamId}
-          teamToken={teamToken}
          chatForm={chatForm}
+          appId={appId}
        />
      )}
      {/* user feedback modal */}
@@ -1063,5 +1086,14 @@ const ChatBox = (
    </Flex>
  );
 };
+const ForwardChatBox = forwardRef(ChatBox);

-export default React.memo(forwardRef(ChatBox));
+const ChatBoxContainer = (props: Props, ref: ForwardedRef<ComponentRef>) => {
+  return (
+    <ChatProvider {...props}>
+      <ForwardChatBox {...props} ref={ref} />
+    </ChatProvider>
+  );
+};
+
+export default React.memo(forwardRef(ChatBoxContainer));
--- a/projects/app/src/components/core/ai/SettingLLMModel/index.tsx
+++ b/projects/app/src/components/core/ai/SettingLLMModel/index.tsx
@@ -55,7 +55,7 @@ const SettingLLMModel = ({ llmModelType = LLMModelTypeEnum.all, defaultData, onC
        leftIcon={
          <Avatar
            borderRadius={'0'}
-            src={selectedModel.avatar || HUGGING_FACE_ICON}
+            src={selectedModel?.avatar || HUGGING_FACE_ICON}
            fallbackSrc={HUGGING_FACE_ICON}
            w={'18px'}
          />
--- a/projects/app/src/components/core/module/Flow/components/modules/QGSwitch.tsx
+++ b/projects/app/src/components/core/module/Flow/components/modules/QGSwitch.tsx
--- a/projects/app/src/components/core/module/Flow/components/modules/TTSSelect.tsx
+++ b/projects/app/src/components/core/module/Flow/components/modules/TTSSelect.tsx
@@ -5,7 +5,7 @@ import { Box, Button, Flex, ModalBody, useDisclosure, Image } from '@chakra-ui/r
 import React, { useCallback, useMemo } from 'react';
 import { useTranslation } from 'next-i18next';
 import { TTSTypeEnum } from '@/constants/app';
-import type { AppTTSConfigType } from '@fastgpt/global/core/module/type.d';
+import type { AppTTSConfigType } from '@fastgpt/global/core/app/type.d';
 import { useAudioPlay } from '@/web/common/utils/voice';
 import { useSystemStore } from '@/web/common/system/useSystemStore';
 import MyModal from '@fastgpt/web/components/common/MyModal';
@@ -46,7 +46,9 @@ const TTSSelect = ({
    [formatValue, list, t]
  );

-  const { playAudio, cancelAudio, audioLoading, audioPlaying } = useAudioPlay({ ttsConfig: value });
+  const { playAudioByText, cancelAudio, audioLoading, audioPlaying } = useAudioPlay({
+    ttsConfig: value
+  });

  const onclickChange = useCallback(
    (e: string) => {
@@ -137,9 +139,7 @@ const TTSSelect = ({
                    color={'primary.600'}
                    isLoading={audioLoading}
                    leftIcon={<MyIcon name={'core/chat/stopSpeech'} w={'16px'} />}
-                    onClick={() => {
-                      cancelAudio();
-                    }}
+                    onClick={cancelAudio}
                  >
                    {t('core.chat.tts.Stop Speech')}
                  </Button>
@@ -149,7 +149,7 @@ const TTSSelect = ({
                  isLoading={audioLoading}
                  leftIcon={<MyIcon name={'core/app/headphones'} w={'16px'} />}
                  onClick={() => {
-                    playAudio({
+                    playAudioByText({
                      text: t('core.app.tts.Test Listen Text')
                    });
                  }}
--- a/projects/app/src/components/core/module/Flow/components/modules/VariableEdit.tsx
+++ b/projects/app/src/components/core/module/Flow/components/modules/VariableEdit.tsx
@@ -26,7 +26,7 @@ import {
 } from '@chakra-ui/react';
 import { QuestionOutlineIcon, SmallAddIcon } from '@chakra-ui/icons';
 import { VariableInputEnum, variableMap } from '@fastgpt/global/core/module/constants';
-import type { VariableItemType } from '@fastgpt/global/core/module/type.d';
+import type { VariableItemType } from '@fastgpt/global/core/app/type.d';
 import MyIcon from '@fastgpt/web/components/common/Icon';
 import { useForm } from 'react-hook-form';
 import { useFieldArray } from 'react-hook-form';
--- a/projects/app/src/components/core/app/WhisperConfig.tsx
+++ b/projects/app/src/components/core/app/WhisperConfig.tsx
@@ -0,0 +1,116 @@
+import MyIcon from '@fastgpt/web/components/common/Icon';
+import MyTooltip from '@/components/MyTooltip';
+import { Box, Button, Flex, ModalBody, useDisclosure, Switch } from '@chakra-ui/react';
+import React, { useMemo } from 'react';
+import { useTranslation } from 'next-i18next';
+import type { AppWhisperConfigType } from '@fastgpt/global/core/app/type.d';
+import MyModal from '@fastgpt/web/components/common/MyModal';
+import QuestionTip from '@fastgpt/web/components/common/MyTooltip/QuestionTip';
+
+const WhisperConfig = ({
+  isOpenAudio,
+  value,
+  onChange
+}: {
+  isOpenAudio: boolean;
+  value: AppWhisperConfigType;
+  onChange: (e: AppWhisperConfigType) => void;
+}) => {
+  const { t } = useTranslation();
+  const { isOpen, onOpen, onClose } = useDisclosure();
+
+  const isOpenWhisper = value.open;
+  const isAutoSend = value.autoSend;
+
+  const formLabel = useMemo(() => {
+    if (!isOpenWhisper) {
+      return t('core.app.whisper.Close');
+    }
+    return t('core.app.whisper.Open');
+  }, [t, isOpenWhisper]);
+
+  return (
+    <Flex alignItems={'center'}>
+      <MyIcon name={'core/app/simpleMode/whisper'} mr={2} w={'20px'} />
+      <Box>{t('core.app.Whisper')}</Box>
+      <Box flex={1} />
+      <MyTooltip label={t('core.app.Config whisper')}>
+        <Button
+          variant={'transparentBase'}
+          iconSpacing={1}
+          size={'sm'}
+          fontSize={'md'}
+          mr={'-5px'}
+          onClick={onOpen}
+        >
+          {formLabel}
+        </Button>
+      </MyTooltip>
+      <MyModal
+        title={t('core.app.Whisper config')}
+        iconSrc="core/app/simpleMode/whisper"
+        isOpen={isOpen}
+        onClose={onClose}
+      >
+        <ModalBody px={[5, 16]} py={[4, 8]}>
+          <Flex justifyContent={'space-between'} alignItems={'center'}>
+            {t('core.app.whisper.Switch')}
+            <Switch
+              isChecked={isOpenWhisper}
+              size={'lg'}
+              onChange={(e) => {
+                onChange({
+                  ...value,
+                  open: e.target.checked
+                });
+              }}
+            />
+          </Flex>
+          {isOpenWhisper && (
+            <Flex mt={8} alignItems={'center'}>
+              {t('core.app.whisper.Auto send')}
+              <QuestionTip label={t('core.app.whisper.Auto send tip')} />
+              <Box flex={'1 0 0'} />
+              <Switch
+                isChecked={value.autoSend}
+                size={'lg'}
+                onChange={(e) => {
+                  onChange({
+                    ...value,
+                    autoSend: e.target.checked
+                  });
+                }}
+              />
+            </Flex>
+          )}
+          {isOpenWhisper && isAutoSend && (
+            <>
+              <Flex mt={8} alignItems={'center'}>
+                {t('core.app.whisper.Auto tts response')}
+                <QuestionTip label={t('core.app.whisper.Auto tts response tip')} />
+                <Box flex={'1 0 0'} />
+                <Switch
+                  isChecked={value.autoTTSResponse}
+                  size={'lg'}
+                  onChange={(e) => {
+                    onChange({
+                      ...value,
+                      autoTTSResponse: e.target.checked
+                    });
+                  }}
+                />
+              </Flex>
+              {!isOpenAudio && (
+                <Box mt={1} color={'myGray.600'} fontSize={'sm'}>
+                  {t('core.app.whisper.Not tts tip')}
+                </Box>
+              )}
+            </>
+          )}
+        </ModalBody>
+      </MyModal>
+    </Flex>
+  );
+};
+
+export default React.memo(WhisperConfig);
--- a/projects/app/src/components/core/module/Flow/ChatTest.tsx
+++ b/projects/app/src/components/core/module/Flow/ChatTest.tsx
@@ -121,6 +121,7 @@ const ChatTest = (
        <Box flex={1}>
          <ChatBox
            ref={ChatBoxRef}
+            appId={app._id}
            appAvatar={app.avatar}
            userAvatar={userInfo?.avatar}
            showMarkIcon
--- a/projects/app/src/components/core/module/Flow/components/nodes/NodeLaf.tsx
+++ b/projects/app/src/components/core/module/Flow/components/nodes/NodeLaf.tsx
@@ -16,13 +16,17 @@ import { useSystemStore } from '@/web/common/system/useSystemStore';
 import { ChevronRightIcon } from '@chakra-ui/icons';
 import { useQuery } from '@tanstack/react-query';
 import dynamic from 'next/dynamic';
-import { FlowNodeInputTypeEnum } from '@fastgpt/global/core/module/node/constant';
+import {
+  FlowNodeInputTypeEnum,
+  FlowNodeOutputTypeEnum
+} from '@fastgpt/global/core/module/node/constant';
 import { useToast } from '@fastgpt/web/hooks/useToast';
 import Divider from '../modules/Divider';
 import RenderToolInput from '../render/RenderToolInput';
 import RenderInput from '../render/RenderInput';
 import RenderOutput from '../render/RenderOutput';
 import { getErrText } from '@fastgpt/global/common/error/utils';
+import { useRequest } from '@fastgpt/web/hooks/useRequest';

 const LafAccountModal = dynamic(() => import('@/components/support/laf/LafAccountModal'));

@@ -31,7 +35,7 @@ const NodeLaf = (props: NodeProps<FlowModuleItemType>) => {
  const { toast } = useToast();
  const { feConfigs } = useSystemStore();
  const { data, selected } = props;
-  const { moduleId, inputs } = data;
+  const { moduleId, inputs, outputs } = data;

  const requestUrl = inputs.find((item) => item.key === ModuleInputKeyEnum.httpReqUrl);

@@ -49,7 +53,11 @@ const NodeLaf = (props: NodeProps<FlowModuleItemType>) => {
    );
  }

-  const { data: lafData, isLoading: isLoadingFunctions } = useQuery(
+  const {
+    data: lafData,
+    isLoading: isLoadingFunctions,
+    refetch: refetchFunction
+  } = useQuery(
    ['getLafFunctionList'],
    async () => {
      // load laf app detail
@@ -94,61 +102,99 @@ const NodeLaf = (props: NodeProps<FlowModuleItemType>) => {
    [lafFunctionSelectList, requestUrl?.value]
  );

-  const onSyncParams = useCallback(() => {
-    const lafFunction = lafData?.lafFunctions.find((item) => item.requestUrl === selectedFunction);
+  const { mutate: onSyncParams, isLoading: isSyncing } = useRequest({
+    mutationFn: async () => {
+      await refetchFunction();
+      const lafFunction = lafData?.lafFunctions.find(
+        (item) => item.requestUrl === selectedFunction
+      );

-    if (!lafFunction) return;
+      if (!lafFunction) return;

-    const bodyParams =
-      lafFunction?.request?.content?.['application/json']?.schema?.properties || {};
+      const bodyParams =
+        lafFunction?.request?.content?.['application/json']?.schema?.properties || {};

-    const requiredParams =
-      lafFunction?.request?.content?.['application/json']?.schema?.required || [];
+      const requiredParams =
+        lafFunction?.request?.content?.['application/json']?.schema?.required || [];

-    const allParams = [
-      ...Object.keys(bodyParams).map((key) => ({
-        name: key,
-        desc: bodyParams[key].description,
-        required: requiredParams?.includes(key) || false,
-        value: `{{${key}}}`,
-        type: 'string'
-      }))
-    ].filter((item) => !inputs.find((input) => input.key === item.name));
+      const allParams = [
+        ...Object.keys(bodyParams).map((key) => ({
+          name: key,
+          desc: bodyParams[key].description,
+          required: requiredParams?.includes(key) || false,
+          value: `{{${key}}}`,
+          type: 'string'
+        }))
+      ].filter((item) => !inputs.find((input) => input.key === item.name));

-    // add params
-    allParams.forEach((param) => {
-      onChangeNode({
-        moduleId,
-        type: 'addInput',
-        key: param.name,
-        value: {
+      // add params
+      allParams.forEach((param) => {
+        onChangeNode({
+          moduleId,
+          type: 'addInput',
          key: param.name,
-          valueType: ModuleIOValueTypeEnum.string,
-          label: param.name,
-          type: FlowNodeInputTypeEnum.target,
-          required: param.required,
-          description: param.desc || '',
-          toolDescription: param.desc || '未设置参数描述',
-          edit: true,
-          editField: {
-            key: true,
-            name: true,
-            description: true,
-            required: true,
-            dataType: true,
-            inputType: true,
-            isToolInput: true
-          },
-          connected: false
-        }
+          value: {
+            key: param.name,
+            valueType: ModuleIOValueTypeEnum.string,
+            label: param.name,
+            type: FlowNodeInputTypeEnum.target,
+            required: param.required,
+            description: param.desc || '',
+            toolDescription: param.desc || '未设置参数描述',
+            edit: true,
+            editField: {
+              key: true,
+              name: true,
+              description: true,
+              required: true,
+              dataType: true,
+              inputType: true,
+              isToolInput: true
+            },
+            connected: false
+          }
+        });
      });
-    });

-    toast({
-      status: 'success',
-      title: t('common.Sync success')
-    });
-  }, [inputs, lafData?.lafFunctions, moduleId, selectedFunction, t, toast]);
+      const responseParams =
+        lafFunction?.response?.default.content?.['application/json'].schema.properties || {};
+      const requiredResponseParams =
+        lafFunction?.response?.default.content?.['application/json'].schema.required || [];
+
+      const allResponseParams = [
+        ...Object.keys(responseParams).map((key) => ({
+          valueType: responseParams[key].type,
+          name: key,
+          desc: responseParams[key].description,
+          required: requiredResponseParams?.includes(key) || false
+        }))
+      ].filter((item) => !outputs.find((output) => output.key === item.name));
+      allResponseParams.forEach((param) => {
+        onChangeNode({
+          moduleId,
+          type: 'addOutput',
+          key: param.name,
+          value: {
+            key: param.name,
+            valueType: param.valueType,
+            label: param.name,
+            type: FlowNodeOutputTypeEnum.source,
+            required: param.required,
+            description: param.desc || '',
+            edit: true,
+            editField: {
+              key: true,
+              description: true,
+              dataType: true,
+              defaultValue: true
+            },
+            targets: []
+          }
+        });
+      });
+    },
+    successToast: t('common.Sync success')
+  });

  return (
    <NodeCard minW={'350px'} selected={selected} {...data}>
@@ -174,9 +220,9 @@ const NodeLaf = (props: NodeProps<FlowModuleItemType>) => {
        {/* auto set params and go to edit */}
        {!!selectedFunction && (
          <Flex justifyContent={'flex-end'} mt={2} gap={2}>
-            {/* <Button variant={'whiteBase'} size={'sm'} onClick={onSyncParams}>
+            <Button isLoading={isSyncing} variant={'grayBase'} size={'sm'} onClick={onSyncParams}>
              {t('core.module.Laf sync params')}
-            </Button> */}
+            </Button>
            <Button
              variant={'grayBase'}
              size={'sm'}
--- a/projects/app/src/components/core/module/Flow/components/nodes/NodeUserGuide.tsx
+++ b/projects/app/src/components/core/module/Flow/components/nodes/NodeUserGuide.tsx
@@ -7,14 +7,14 @@ import { ModuleInputKeyEnum } from '@fastgpt/global/core/module/constants';
 import { welcomeTextTip } from '@fastgpt/global/core/module/template/tip';
 import { onChangeNode } from '../../FlowProvider';

-import VariableEdit from '../modules/VariableEdit';
+import VariableEdit from '../../../../app/VariableEdit';
 import MyIcon from '@fastgpt/web/components/common/Icon';
 import MyTooltip from '@/components/MyTooltip';
 import Container from '../modules/Container';
 import NodeCard from '../render/NodeCard';
-import type { VariableItemType } from '@fastgpt/global/core/module/type.d';
-import QGSwitch from '@/components/core/module/Flow/components/modules/QGSwitch';
-import TTSSelect from '@/components/core/module/Flow/components/modules/TTSSelect';
+import type { VariableItemType } from '@fastgpt/global/core/app/type.d';
+import QGSwitch from '@/components/core/app/QGSwitch';
+import TTSSelect from '@/components/core/app/TTSSelect';
 import { splitGuideModule } from '@fastgpt/global/core/module/utils';
 import { useTranslation } from 'next-i18next';

--- a/projects/app/src/global/core/chat/api.d.ts
+++ b/projects/app/src/global/core/chat/api.d.ts
@@ -1,4 +1,4 @@
-import type { AppTTSConfigType } from '@fastgpt/global/core/module/type.d';
+import type { AppTTSConfigType } from '@fastgpt/global/core/app/type.d';
 import { ModuleItemType } from '../module/type';
 import { AdminFbkType, ChatItemType } from '@fastgpt/global/core/chat/type';
 import type { OutLinkChatAuthProps } from '@fastgpt/global/support/permission/chat.d';
--- a/projects/app/src/pages/api/core/chat/item/getSpeech.ts
+++ b/projects/app/src/pages/api/core/chat/item/getSpeech.ts
@@ -12,7 +12,6 @@ import { MongoTTSBuffer } from '@fastgpt/service/common/buffer/tts/schema';
 /* 
 1. get tts from chatItem store
 2. get tts from ai
-3. save tts to chatItem store if chatItemId is provided
 4. push bill
 */

@@ -34,6 +33,7 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse)
      throw new Error('voice not found');
    }

+    /* get audio from buffer */
    const ttsBuffer = await MongoTTSBuffer.findOne(
      {
        bufferId: voiceData.bufferId,
@@ -46,6 +46,7 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse)
      return res.end(new Uint8Array(ttsBuffer.buffer.buffer));
    }

+    /* request audio */
    await text2Speech({
      res,
      input,
@@ -54,6 +55,7 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse)
      speed: ttsConfig.speed,
      onSuccess: async ({ model, buffer }) => {
        try {
+          /* bill */
          pushAudioSpeechUsage({
            model: model,
            charsLength: input.length,
@@ -62,6 +64,7 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse)
            source: authType2UsageSource({ authType })
          });

+          /* create buffer */
          await MongoTTSBuffer.create({
            bufferId: voiceData.bufferId,
            text: JSON.stringify({ text: input, speed: ttsConfig.speed }),
--- a/projects/app/src/pages/api/v1/audio/transcriptions.ts
+++ b/projects/app/src/pages/api/v1/audio/transcriptions.ts
@@ -7,6 +7,8 @@ import fs from 'fs';
 import { getAIApi } from '@fastgpt/service/core/ai/config';
 import { pushWhisperUsage } from '@/service/support/wallet/usage/push';
 import { authChatCert } from '@/service/support/permission/auth/chat';
+import { MongoApp } from '@fastgpt/service/core/app/schema';
+import { getGuideModule, splitGuideModule } from '@fastgpt/global/core/module/utils';

 const upload = getUploadModel({
  maxSize: 2
@@ -18,8 +20,9 @@ export default withNextCors(async function handler(req: NextApiRequest, res: Nex
  try {
    const {
      file,
-      data: { duration, teamId: spaceTeamId, teamToken }
+      data: { appId, duration, teamId: spaceTeamId, teamToken }
    } = await upload.doUpload<{
+      appId: string;
      duration: number;
      shareId?: string;
      teamId?: string;
@@ -31,8 +34,6 @@ export default withNextCors(async function handler(req: NextApiRequest, res: Nex

    filePaths = [file.path];

-    const { teamId, tmbId } = await authChatCert({ req, authToken: true });
-
    if (!global.whisperModel) {
      throw new Error('whisper model not found');
    }
@@ -41,6 +42,18 @@ export default withNextCors(async function handler(req: NextApiRequest, res: Nex
      throw new Error('file not found');
    }

+    // auth role
+    const { teamId, tmbId } = await authChatCert({ req, authToken: true });
+    // auth app
+    const app = await MongoApp.findById(appId, 'modules').lean();
+    if (!app) {
+      throw new Error('app not found');
+    }
+    const { whisperConfig } = splitGuideModule(getGuideModule(app?.modules));
+    if (!whisperConfig?.open) {
+      throw new Error('Whisper is not open in the app');
+    }
+
    const ai = getAIApi();

    const result = await ai.audio.transcriptions.create({
--- a/projects/app/src/pages/app/detail/components/Logs.tsx
+++ b/projects/app/src/pages/app/detail/components/Logs.tsx
@@ -32,6 +32,7 @@ import MyBox from '@/components/common/MyBox';
 import { usePagination } from '@fastgpt/web/hooks/usePagination';
 import DateRangePicker, { DateRangeType } from '@fastgpt/web/components/common/DateRangePicker';
 import { formatChatValue2InputType } from '@/components/ChatBox/utils';
+import { getNanoid } from '@fastgpt/global/common/string/tools';

 const Logs = ({ appId }: { appId: string }) => {
  const { t } = useTranslation();
@@ -234,6 +235,7 @@ const DetailLogsModal = ({
      onSuccess(res) {
        const history = res.history.map((item) => ({
          ...item,
+          dataId: item.dataId || getNanoid(),
          status: 'finish' as any
        }));
        ChatBoxRef.current?.resetHistory(history);
--- a/projects/app/src/pages/app/detail/components/SimpleEdit/ChatTest.tsx
+++ b/projects/app/src/pages/app/detail/components/SimpleEdit/ChatTest.tsx
@@ -99,6 +99,7 @@ const ChatTest = ({ appId }: { appId: string }) => {
      <Box flex={1}>
        <ChatBox
          ref={ChatBoxRef}
+          appId={appDetail._id}
          appAvatar={appDetail.avatar}
          userAvatar={userInfo?.avatar}
          showMarkIcon
--- a/projects/app/src/pages/app/detail/components/SimpleEdit/EditForm.tsx
+++ b/projects/app/src/pages/app/detail/components/SimpleEdit/EditForm.tsx
@@ -6,7 +6,7 @@ import { useForm, useFieldArray } from 'react-hook-form';
 import { useSystemStore } from '@/web/common/system/useSystemStore';
 import { appModules2Form, getDefaultAppForm } from '@fastgpt/global/core/app/utils';
 import type { AppSimpleEditFormType } from '@fastgpt/global/core/app/type.d';
-import { chatNodeSystemPromptTip, welcomeTextTip } from '@fastgpt/global/core/module/template/tip';
+import { welcomeTextTip } from '@fastgpt/global/core/module/template/tip';
 import { useRequest } from '@fastgpt/web/hooks/useRequest';
 import { useConfirm } from '@fastgpt/web/hooks/useConfirm';
 import { useRouter } from 'next/router';
@@ -20,7 +20,7 @@ import dynamic from 'next/dynamic';
 import MyTooltip from '@/components/MyTooltip';
 import Avatar from '@/components/Avatar';
 import MyIcon from '@fastgpt/web/components/common/Icon';
-import VariableEdit from '@/components/core/module/Flow/components/modules/VariableEdit';
+import VariableEdit from '@/components/core/app/VariableEdit';
 import MyTextarea from '@/components/common/Textarea/MyTextarea/index';
 import PromptEditor from '@fastgpt/web/components/common/Textarea/PromptEditor';
 import { formatEditorVariablePickerIcon } from '@fastgpt/global/core/module/utils';
@@ -28,14 +28,26 @@ import SearchParamsTip from '@/components/core/dataset/SearchParamsTip';
 import SettingLLMModel from '@/components/core/ai/SettingLLMModel';
 import { SettingAIDataType } from '@fastgpt/global/core/module/node/type';
 import DeleteIcon, { hoverDeleteStyles } from '@fastgpt/web/components/common/Icon/delete';
+import { TTSTypeEnum } from '@/constants/app';

 const DatasetSelectModal = dynamic(() => import('@/components/core/module/DatasetSelectModal'));
 const DatasetParamsModal = dynamic(() => import('@/components/core/module/DatasetParamsModal'));
 const ToolSelectModal = dynamic(() => import('./ToolSelectModal'));
-const TTSSelect = dynamic(
-  () => import('@/components/core/module/Flow/components/modules/TTSSelect')
-);
-const QGSwitch = dynamic(() => import('@/components/core/module/Flow/components/modules/QGSwitch'));
+const TTSSelect = dynamic(() => import('@/components/core/app/TTSSelect'));
+const QGSwitch = dynamic(() => import('@/components/core/app/QGSwitch'));
+const WhisperConfig = dynamic(() => import('@/components/core/app/WhisperConfig'));
+
+const BoxStyles: BoxProps = {
+  px: 5,
+  py: '16px',
+  borderBottomWidth: '1px',
+  borderBottomColor: 'borderColor.low'
+};
+const LabelStyles: BoxProps = {
+  w: ['60px', '100px'],
+  flexShrink: 0,
+  fontSize: ['sm', 'md']
+};

 const EditForm = ({
  divRef,
@@ -131,18 +143,6 @@ const EditForm = ({
  );
  useQuery(['loadAllDatasets'], loadAllDatasets);

-  const BoxStyles: BoxProps = {
-    px: 5,
-    py: '16px',
-    borderBottomWidth: '1px',
-    borderBottomColor: 'borderColor.low'
-  };
-  const LabelStyles: BoxProps = {
-    w: ['60px', '100px'],
-    flexShrink: 0,
-    fontSize: ['sm', 'md']
-  };
-
  return (
    <Box>
      {/* title */}
@@ -154,7 +154,7 @@ const EditForm = ({
        py={4}
        justifyContent={'space-between'}
        alignItems={'center'}
-        zIndex={10}
+        zIndex={100}
        px={4}
        {...(isSticky && {
          borderBottom: theme.borders.base,
@@ -414,6 +414,18 @@ const EditForm = ({
            />
          </Box>

+          {/* whisper */}
+          <Box {...BoxStyles}>
+            <WhisperConfig
+              isOpenAudio={getValues('userGuide.tts').type !== TTSTypeEnum.none}
+              value={getValues('userGuide.whisper')}
+              onChange={(e) => {
+                setValue('userGuide.whisper', e);
+                setRefresh((state) => !state);
+              }}
+            />
+          </Box>
+
          {/* question guide */}
          <Box {...BoxStyles} borderBottom={'none'}>
            <QGSwitch
--- a/projects/app/src/pages/chat/index.tsx
+++ b/projects/app/src/pages/chat/index.tsx
@@ -146,6 +146,7 @@ const Chat = ({ appId, chatId }: { appId: string; chatId: string }) => {
        const res = await getInitChatInfo({ appId, chatId });
        const history = res.history.map((item) => ({
          ...item,
+          dataId: item.dataId || nanoid(),
          status: ChatStatusEnum.finish
        }));

--- a/projects/app/src/pages/chat/share.tsx
+++ b/projects/app/src/pages/chat/share.tsx
@@ -141,6 +141,7 @@ const OutLink = ({
      /* post message to report result */
      const result: ChatSiteItemType[] = GPTMessages2Chats(prompts).map((item) => ({
        ...item,
+        dataId: item.dataId || nanoid(),
        status: 'finish'
      }));

@@ -183,6 +184,7 @@ const OutLink = ({
        });
        const history = res.history.map((item) => ({
          ...item,
+          dataId: item.dataId || nanoid(),
          status: ChatStatusEnum.finish
        }));

--- a/projects/app/src/pages/chat/team.tsx
+++ b/projects/app/src/pages/chat/team.tsx
@@ -210,6 +210,7 @@ const OutLink = () => {

      const history = res.history.map((item) => ({
        ...item,
+        dataId: item.dataId || nanoid(),
        status: ChatStatusEnum.finish
      }));

--- a/projects/app/src/web/common/hooks/useSpeech.ts
+++ b/projects/app/src/web/common/hooks/useSpeech.ts
@@ -5,7 +5,7 @@ import { useTranslation } from 'next-i18next';
 import { getErrText } from '@fastgpt/global/common/error/utils';
 import { OutLinkChatAuthProps } from '@fastgpt/global/support/permission/chat';

-export const useSpeech = (props?: OutLinkChatAuthProps) => {
+export const useSpeech = (props?: OutLinkChatAuthProps & { appId?: string }) => {
  const { t } = useTranslation();
  const mediaRecorder = useRef<MediaRecorder>();
  const [mediaStream, setMediaStream] = useState<MediaStream>();
@@ -15,6 +15,7 @@ export const useSpeech = (props?: OutLinkChatAuthProps) => {
  const [audioSecond, setAudioSecond] = useState(0);
  const intervalRef = useRef<any>();
  const startTimestamp = useRef(0);
+  const cancelWhisperSignal = useRef(false);

  const speakingTimeString = useMemo(() => {
    const minutes: number = Math.floor(audioSecond / 60);
@@ -51,6 +52,8 @@ export const useSpeech = (props?: OutLinkChatAuthProps) => {

  const startSpeak = async (onFinish: (text: string) => void) => {
    try {
+      cancelWhisperSignal.current = false;
+
      const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
      setMediaStream(stream);

@@ -73,42 +76,45 @@ export const useSpeech = (props?: OutLinkChatAuthProps) => {
      };

      mediaRecorder.current.onstop = async () => {
-        const formData = new FormData();
-        let options = {};
-        if (MediaRecorder.isTypeSupported('audio/webm')) {
-          options = { type: 'audio/webm' };
-        } else if (MediaRecorder.isTypeSupported('video/mp3')) {
-          options = { type: 'video/mp3' };
-        } else {
-          console.error('no suitable mimetype found for this device');
-        }
-        const blob = new Blob(chunks, options);
-        const duration = Math.round((Date.now() - startTimestamp.current) / 1000);
+        if (!cancelWhisperSignal.current) {
+          const formData = new FormData();
+          let options = {};
+          if (MediaRecorder.isTypeSupported('audio/webm')) {
+            options = { type: 'audio/webm' };
+          } else if (MediaRecorder.isTypeSupported('video/mp3')) {
+            options = { type: 'video/mp3' };
+          } else {
+            console.error('no suitable mimetype found for this device');
+          }
+          const blob = new Blob(chunks, options);
+          const duration = Math.round((Date.now() - startTimestamp.current) / 1000);

-        formData.append('file', blob, 'recording.mp3');
-        formData.append(
-          'data',
-          JSON.stringify({
-            ...props,
-            duration
-          })
-        );
+          formData.append('file', blob, 'recording.mp3');
+          formData.append(
+            'data',
+            JSON.stringify({
+              ...props,
+              duration
+            })
+          );

-        setIsTransCription(true);
-        try {
-          const result = await POST<string>('/v1/audio/transcriptions', formData, {
-            timeout: 60000,
-            headers: {
-              'Content-Type': 'multipart/form-data; charset=utf-8'
-            }
-          });
-          onFinish(result);
-        } catch (error) {
-          toast({
-            status: 'warning',
-            title: getErrText(error, t('common.speech.error tip'))
-          });
+          setIsTransCription(true);
+          try {
+            const result = await POST<string>('/v1/audio/transcriptions', formData, {
+              timeout: 60000,
+              headers: {
+                'Content-Type': 'multipart/form-data; charset=utf-8'
+              }
+            });
+            onFinish(result);
+          } catch (error) {
+            toast({
+              status: 'warning',
+              title: getErrText(error, t('common.speech.error tip'))
+            });
+          }
        }
+
        setIsTransCription(false);
        setIsSpeaking(false);
      };
@@ -128,7 +134,8 @@ export const useSpeech = (props?: OutLinkChatAuthProps) => {
    }
  };

-  const stopSpeak = () => {
+  const stopSpeak = (cancel = false) => {
+    cancelWhisperSignal.current = cancel;
    if (mediaRecorder.current) {
      mediaRecorder.current?.stop();
      clearInterval(intervalRef.current);
@@ -147,6 +154,13 @@ export const useSpeech = (props?: OutLinkChatAuthProps) => {
    };
  }, []);

+  // listen minuted. over 60 seconds, stop speak
+  useEffect(() => {
+    if (audioSecond >= 60) {
+      stopSpeak();
+    }
+  }, [audioSecond]);
+
  return {
    startSpeak,
    stopSpeak,
--- a/projects/app/src/web/common/utils/voice.ts
+++ b/projects/app/src/web/common/utils/voice.ts
@@ -1,246 +1,357 @@
 import { useState, useCallback, useEffect, useMemo, useRef } from 'react';
 import { useToast } from '@fastgpt/web/hooks/useToast';
 import { getErrText } from '@fastgpt/global/common/error/utils';
-import type { AppTTSConfigType } from '@fastgpt/global/core/module/type.d';
+import type { AppTTSConfigType } from '@fastgpt/global/core/app/type.d';
 import { TTSTypeEnum } from '@/constants/app';
 import { useTranslation } from 'next-i18next';
 import type { OutLinkChatAuthProps } from '@fastgpt/global/support/permission/chat.d';

+const contentType = 'audio/mpeg';
+const splitMarker = 'SPLIT_MARKER';
+
 export const useAudioPlay = (props?: OutLinkChatAuthProps & { ttsConfig?: AppTTSConfigType }) => {
  const { t } = useTranslation();
  const { ttsConfig, shareId, outLinkUid, teamId, teamToken } = props || {};
  const { toast } = useToast();
-  const [audio, setAudio] = useState<HTMLAudioElement>();
+  const audioRef = useRef<HTMLAudioElement>(new Audio());
+  const audio = audioRef.current;
  const [audioLoading, setAudioLoading] = useState(false);
  const [audioPlaying, setAudioPlaying] = useState(false);
  const audioController = useRef(new AbortController());

  // Check whether the voice is supported
-  const hasAudio = useMemo(() => {
+  const hasAudio = (() => {
    if (ttsConfig?.type === TTSTypeEnum.none) return false;
    if (ttsConfig?.type === TTSTypeEnum.model) return true;
    const voices = window.speechSynthesis?.getVoices?.() || []; // 获取语言包
    const voice = voices.find((item) => {
-      return item.lang === 'zh-CN';
+      return item.lang === 'zh-CN' || item.lang === 'zh';
    });
    return !!voice;
-  }, [ttsConfig]);
+  })();

-  const playAudio = async ({
-    text,
-    chatItemId,
-    buffer
-  }: {
-    text: string;
-    chatItemId?: string;
-    buffer?: Uint8Array;
-  }) =>
-    new Promise<{ buffer?: Uint8Array }>(async (resolve, reject) => {
-      text = text.replace(/\\n/g, '\n');
-      try {
-        // tts play
-        if (audio && ttsConfig && ttsConfig?.type === TTSTypeEnum.model) {
-          setAudioLoading(true);
+  const getAudioStream = useCallback(
+    async (input: string) => {
+      if (!input) return Promise.reject('Text is empty');

-          /* buffer tts */
-          if (buffer) {
-            playAudioBuffer({ audio, buffer });
-            setAudioLoading(false);
-            return resolve({ buffer });
-          }
+      setAudioLoading(true);
+      audioController.current = new AbortController();

-          audioController.current = new AbortController();
+      const response = await fetch('/api/core/chat/item/getSpeech', {
+        method: 'POST',
+        headers: {
+          'Content-Type': 'application/json'
+        },
+        signal: audioController.current.signal,
+        body: JSON.stringify({
+          ttsConfig,
+          input: input.trim(),
+          shareId,
+          outLinkUid,
+          teamId,
+          teamToken
+        })
+      }).finally(() => {
+        setAudioLoading(false);
+      });

-          /* request tts */
-          const response = await fetch('/api/core/chat/item/getSpeech', {
-            method: 'POST',
-            headers: {
-              'Content-Type': 'application/json'
-            },
-            signal: audioController.current.signal,
-            body: JSON.stringify({
-              chatItemId,
-              ttsConfig,
-              input: text,
-              shareId,
-              outLinkUid,
-              teamId,
-              teamToken
-            })
-          });
-          setAudioLoading(false);
-
-          if (!response.body || !response.ok) {
-            const data = await response.json();
-            toast({
-              status: 'error',
-              title: getErrText(data, t('core.chat.Audio Speech Error'))
-            });
-            return reject(data);
-          }
-
-          const audioBuffer = await readAudioStream({
-            audio,
-            stream: response.body,
-            contentType: 'audio/mpeg'
-          });
-
-          resolve({
-            buffer: audioBuffer
-          });
-        } else {
-          // window speech
-          window.speechSynthesis?.cancel();
-          const msg = new SpeechSynthesisUtterance(text);
-          const voices = window.speechSynthesis?.getVoices?.() || []; // 获取语言包
-          const voice = voices.find((item) => {
-            return item.lang === 'zh-CN';
-          });
-          if (voice) {
-            msg.onstart = () => {
-              setAudioPlaying(true);
-            };
-            msg.onend = () => {
-              setAudioPlaying(false);
-              msg.onstart = null;
-              msg.onend = null;
-            };
-            msg.voice = voice;
-            window.speechSynthesis?.speak(msg);
-          }
-          resolve({});
-        }
-      } catch (error) {
+      if (!response.body || !response.ok) {
+        const data = await response.json();
        toast({
          status: 'error',
-          title: getErrText(error, t('core.chat.Audio Speech Error'))
+          title: getErrText(data, t('core.chat.Audio Speech Error'))
        });
-        reject(error);
+        return Promise.reject(data);
      }
-      setAudioLoading(false);
+      return response.body;
+    },
+    [outLinkUid, shareId, t, teamId, teamToken, toast, ttsConfig]
+  );
+  const playWebAudio = useCallback((text: string) => {
+    // window speech
+    window.speechSynthesis?.cancel();
+    const msg = new SpeechSynthesisUtterance(text);
+    const voices = window.speechSynthesis?.getVoices?.() || []; // 获取语言包
+    const voice = voices.find((item) => {
+      return item.lang === 'zh-CN';
    });
-
+    if (voice) {
+      msg.onstart = () => {
+        setAudioPlaying(true);
+      };
+      msg.onend = () => {
+        setAudioPlaying(false);
+        msg.onstart = null;
+        msg.onend = null;
+      };
+      msg.voice = voice;
+      window.speechSynthesis?.speak(msg);
+    }
+  }, []);
  const cancelAudio = useCallback(() => {
+    try {
+      window.speechSynthesis?.cancel();
+      audioController.current.abort('');
+    } catch (error) {}
    if (audio) {
      audio.pause();
      audio.src = '';
    }
-    window.speechSynthesis?.cancel();
-    audioController.current?.abort();
    setAudioPlaying(false);
  }, [audio]);

-  // listen ttsUrl update
-  useEffect(() => {
-    setAudio(new Audio());
+  /* Perform a voice playback */
+  const playAudioByText = useCallback(
+    async ({ text, buffer }: { text: string; buffer?: Uint8Array }) => {
+      const playAudioBuffer = (buffer: Uint8Array) => {
+        const audioUrl = URL.createObjectURL(new Blob([buffer], { type: 'audio/mpeg' }));
+
+        audio.src = audioUrl;
+        audio.play();
+      };
+      const readAudioStream = (stream: ReadableStream<Uint8Array>) => {
+        if (!audio) return;
+
+        // Create media source and play audio
+        const ms = new MediaSource();
+        const url = URL.createObjectURL(ms);
+        audio.src = url;
+        audio.play();
+
+        let u8Arr: Uint8Array = new Uint8Array();
+        return new Promise<Uint8Array>(async (resolve, reject) => {
+          // Async to read data from ms
+          await new Promise((resolve) => {
+            ms.onsourceopen = resolve;
+          });
+          const sourceBuffer = ms.addSourceBuffer(contentType);
+
+          const reader = stream.getReader();
+
+          // read stream
+          try {
+            while (true) {
+              const { done, value } = await reader.read();
+              if (done || audio.paused) {
+                resolve(u8Arr);
+                if (sourceBuffer.updating) {
+                  await new Promise((resolve) => (sourceBuffer.onupdateend = resolve));
+                }
+                ms.endOfStream();
+                return;
+              }
+
+              u8Arr = new Uint8Array([...u8Arr, ...value]);
+
+              await new Promise((resolve) => {
+                sourceBuffer.onupdateend = resolve;
+                sourceBuffer.appendBuffer(value.buffer);
+              });
+            }
+          } catch (error) {
+            reject(error);
+          }
+        });
+      };
+
+      return new Promise<{ buffer?: Uint8Array }>(async (resolve, reject) => {
+        text = text.replace(/\\n/g, '\n');
+        try {
+          // stop last audio
+          cancelAudio();
+
+          // tts play
+          if (audio && ttsConfig?.type === TTSTypeEnum.model) {
+            /* buffer tts */
+            if (buffer) {
+              playAudioBuffer(buffer);
+              return resolve({ buffer });
+            }
+
+            /* request tts */
+            const audioBuffer = await readAudioStream(await getAudioStream(text));
+
+            resolve({
+              buffer: audioBuffer
+            });
+          } else {
+            // window speech
+            playWebAudio(text);
+            resolve({});
+          }
+        } catch (error) {
+          toast({
+            status: 'error',
+            title: getErrText(error, t('core.chat.Audio Speech Error'))
+          });
+          reject(error);
+        }
+      });
+    },
+    [audio, cancelAudio, getAudioStream, playWebAudio, t, toast, ttsConfig?.type]
+  );
+
+  // segmented params
+  const segmentedMediaSource = useRef<MediaSource>();
+  const segmentedSourceBuffer = useRef<SourceBuffer>();
+  const segmentedTextList = useRef<string[]>([]);
+  const appendAudioPromise = useRef<Promise<any>>(Promise.resolve());
+
+  /* Segmented voice playback */
+  const startSegmentedAudio = useCallback(async () => {
+    if (!audio) return;
+    cancelAudio();
+
+    /* reset all source */
+    const buffer = segmentedSourceBuffer.current;
+    if (buffer) {
+      buffer.updating && (await new Promise((resolve) => (buffer.onupdateend = resolve)));
+      segmentedSourceBuffer.current = undefined;
+    }
+    if (segmentedMediaSource.current) {
+      if (segmentedMediaSource.current?.readyState === 'open') {
+        segmentedMediaSource.current.endOfStream();
+      }
+      segmentedMediaSource.current = undefined;
+    }
+
+    /* init source */
+    segmentedTextList.current = [];
+    appendAudioPromise.current = Promise.resolve();
+
+    /* start ms and source buffer */
+    const ms = new MediaSource();
+    segmentedMediaSource.current = ms;
+    const url = URL.createObjectURL(ms);
+    audio.src = url;
+    audio.play();
+
+    await new Promise((resolve) => {
+      ms.onsourceopen = resolve;
+    });
+    const sourceBuffer = ms.addSourceBuffer(contentType);
+    segmentedSourceBuffer.current = sourceBuffer;
+  }, [audio, cancelAudio]);
+  const finishSegmentedAudio = useCallback(() => {
+    appendAudioPromise.current = appendAudioPromise.current.finally(() => {
+      if (segmentedMediaSource.current?.readyState === 'open') {
+        segmentedMediaSource.current.endOfStream();
+      }
+    });
  }, []);

+  const appendAudioStream = useCallback(
+    (input: string) => {
+      const buffer = segmentedSourceBuffer.current;
+
+      if (!buffer) return;
+
+      let u8Arr: Uint8Array = new Uint8Array();
+      return new Promise<Uint8Array>(async (resolve, reject) => {
+        // read stream
+        try {
+          const stream = await getAudioStream(input);
+          const reader = stream.getReader();
+
+          while (true) {
+            const { done, value } = await reader.read();
+
+            if (done || !audio?.played) {
+              buffer.updating && (await new Promise((resolve) => (buffer.onupdateend = resolve)));
+              return resolve(u8Arr);
+            }
+
+            u8Arr = new Uint8Array([...u8Arr, ...value]);
+
+            await new Promise((resolve) => {
+              buffer.onupdateend = resolve;
+              buffer.appendBuffer(value.buffer);
+            });
+          }
+        } catch (error) {
+          reject(error);
+        }
+      });
+    },
+    [audio?.played, getAudioStream, segmentedSourceBuffer]
+  );
+  /* split audio text and fetch tts */
+  const splitText2Audio = useCallback(
+    (text: string, done?: boolean) => {
+      if (ttsConfig?.type === TTSTypeEnum.model && ttsConfig?.model) {
+        const splitReg = /([。！？]|[.!?]\s)/g;
+        const storeText = segmentedTextList.current.join('');
+        const newText = text.slice(storeText.length);
+
+        const splitTexts = newText
+          .replace(splitReg, (() => `$1${splitMarker}`.trim())())
+          .split(`${splitMarker}`)
+          .filter((part) => part.trim());
+
+        if (splitTexts.length > 1 || done) {
+          let splitList = splitTexts.slice();
+
+          // concat same sentence
+          if (!done) {
+            splitList = splitTexts.slice(0, -1);
+            splitList = [splitList.join('')];
+          }
+
+          segmentedTextList.current = segmentedTextList.current.concat(splitList);
+
+          for (const item of splitList) {
+            appendAudioPromise.current = appendAudioPromise.current.then(() =>
+              appendAudioStream(item)
+            );
+          }
+        }
+      } else if (ttsConfig?.type === TTSTypeEnum.web && done) {
+        playWebAudio(text);
+      }
+    },
+    [appendAudioStream, playWebAudio, ttsConfig?.model, ttsConfig?.type]
+  );
+
  // listen audio status
  useEffect(() => {
-    if (audio) {
-      audio.onplay = () => {
-        setAudioPlaying(true);
-      };
-      audio.onended = () => {
-        setAudioPlaying(false);
-      };
-      audio.onerror = () => {
-        setAudioPlaying(false);
-      };
-      audio.oncancel = () => {
-        setAudioPlaying(false);
-      };
-    }
+    audio.onplay = () => {
+      setAudioPlaying(true);
+    };
+    audio.onended = () => {
+      setAudioPlaying(false);
+    };
+    audio.onerror = () => {
+      setAudioPlaying(false);
+    };
+    audio.oncancel = () => {
+      setAudioPlaying(false);
+    };
    const listen = () => {
      cancelAudio();
    };
    window.addEventListener('beforeunload', listen);
    return () => {
-      if (audio) {
-        audio.onplay = null;
-        audio.onended = null;
-        audio.onerror = null;
-      }
+      audio.onplay = null;
+      audio.onended = null;
+      audio.onerror = null;
      cancelAudio();
+      audio.remove();
      window.removeEventListener('beforeunload', listen);
    };
-  }, [audio, cancelAudio]);
-
-  useEffect(() => {
-    return () => {
-      setAudio(undefined);
-    };
  }, []);

  return {
-    audioPlaying,
+    audio,
    audioLoading,
-    hasAudio,
-    playAudio,
-    cancelAudio
+    audioPlaying,
+    setAudioPlaying,
+    getAudioStream,
+    cancelAudio,
+    audioController,
+    hasAudio: useMemo(() => hasAudio, [hasAudio]),
+    playAudioByText,
+    startSegmentedAudio,
+    finishSegmentedAudio,
+    splitText2Audio
  };
 };
-
-export function readAudioStream({
-  audio,
-  stream,
-  contentType = 'audio/mpeg'
-}: {
-  audio: HTMLAudioElement;
-  stream: ReadableStream<Uint8Array>;
-  contentType?: string;
-}): Promise<Uint8Array> {
-  // Create media source and play audio
-  const ms = new MediaSource();
-  const url = URL.createObjectURL(ms);
-  audio.src = url;
-  audio.play();
-
-  let u8Arr: Uint8Array = new Uint8Array();
-  return new Promise<Uint8Array>(async (resolve, reject) => {
-    // Async to read data from ms
-    await new Promise((resolve) => {
-      ms.onsourceopen = resolve;
-    });
-
-    const sourceBuffer = ms.addSourceBuffer(contentType);
-
-    const reader = stream.getReader();
-
-    // read stream
-    try {
-      while (true) {
-        const { done, value } = await reader.read();
-        if (done) {
-          resolve(u8Arr);
-          if (sourceBuffer.updating) {
-            await new Promise((resolve) => (sourceBuffer.onupdateend = resolve));
-          }
-          ms.endOfStream();
-          return;
-        }
-
-        u8Arr = new Uint8Array([...u8Arr, ...value]);
-
-        await new Promise((resolve) => {
-          sourceBuffer.onupdateend = resolve;
-          sourceBuffer.appendBuffer(value.buffer);
-        });
-      }
-    } catch (error) {
-      reject(error);
-    }
-  });
-}
-export function playAudioBuffer({
-  audio,
-  buffer
-}: {
-  audio: HTMLAudioElement;
-  buffer: Uint8Array;
-}) {
-  const audioUrl = URL.createObjectURL(new Blob([buffer], { type: 'audio/mpeg' }));
-
-  audio.src = audioUrl;
-  audio.play();
-}
--- a/projects/app/src/web/core/app/utils.ts
+++ b/projects/app/src/web/core/app/utils.ts
@@ -38,8 +38,14 @@ export async function postForm2Modules(data: AppSimpleEditFormType) {
          {
            key: ModuleInputKeyEnum.tts,
            type: FlowNodeInputTypeEnum.hidden,
-            label: 'core.app.TTS',
+            label: '',
            value: formData.userGuide.tts
+          },
+          {
+            key: ModuleInputKeyEnum.whisper,
+            type: FlowNodeInputTypeEnum.hidden,
+            label: '',
+            value: formData.userGuide.whisper
          }
        ],
        outputs: [],