Refactor listening mode handling and wake word detection configuration

- Replace direct mode setting logic with a new GetDefaultListeningMode method for improved clarity and maintainability.
- Update HandleToggleChatEvent, HandleWakeWordDetectedEvent, and ContinueWakeWordInvoke to utilize the new method for determining listening mode.
- Introduce Kconfig option WAKE_WORD_DETECTION_IN_LISTENING to enable or disable wake word detection during listening mode, enhancing configurability.

.clang-format

@@ -0,0 +1,126 @@
+---
+Language: Cpp
+BasedOnStyle: Google
+AccessModifierOffset: -4
+AlignAfterOpenBracket: Align
+AlignConsecutiveAssignments: false
+AlignConsecutiveDeclarations: false
+AlignEscapedNewlines: Left
+AlignOperands: true
+AlignTrailingComments: true
+AllowAllParametersOfDeclarationOnNextLine: true
+AllowShortBlocksOnASingleLine: false
+AllowShortCaseLabelsOnASingleLine: false
+AllowShortFunctionsOnASingleLine: All
+AllowShortIfStatementsOnASingleLine: false
+AllowShortLoopsOnASingleLine: false
+AlwaysBreakAfterReturnType: ExceptShortType
+AlwaysBreakBeforeMultilineStrings: true
+AlwaysBreakTemplateDeclarations: Yes
+BinPackArguments: true
+BinPackParameters: true
+BraceWrapping:
+  AfterClass: false
+  AfterControlStatement: false
+  AfterEnum: false
+  AfterFunction: false
+  AfterNamespace: false
+  AfterObjCDeclaration: false
+  AfterStruct: false
+  AfterUnion: false
+  AfterExternBlock: false
+  BeforeCatch: false
+  BeforeElse: false
+  IndentBraces: false
+  SplitEmptyFunction: false
+  SplitEmptyRecord: false
+  SplitEmptyNamespace: false
+BreakBeforeBinaryOperators: None
+BreakBeforeBraces: Attach
+BreakBeforeInheritanceComma: false
+BreakInheritanceList: BeforeColon
+BreakBeforeTernaryOperators: true
+BreakConstructorInitializersBeforeComma: false
+BreakConstructorInitializers: BeforeColon
+BreakAfterJavaFieldAnnotations: false
+BreakStringLiterals: true
+ColumnLimit: 100
+CommentPragmas: '^ IWYU pragma:'
+CompactNamespaces: false
+ConstructorInitializerAllOnOneLineOrOnePerLine: true
+ConstructorInitializerIndentWidth: 4
+ContinuationIndentWidth: 4
+Cpp11BracedListStyle: true
+DerivePointerAlignment: false
+DisableFormat: false
+ExperimentalAutoDetectBinPacking: false
+FixNamespaceComments: true
+ForEachMacros:
+  - cJSON_ArrayForEach
+IncludeBlocks: Preserve
+IncludeCategories:
+  - Regex: '^<esp_.*\.h>'
+    Priority: 1
+  - Regex: '^<driver/.*\.h>'
+    Priority: 1
+  - Regex: '^<.*\.h>'
+    Priority: 2
+  - Regex: '^<.*'
+    Priority: 3
+  - Regex: '.*'
+    Priority: 4
+IncludeIsMainRegex: '([-_](test|unittest))?$'
+IndentCaseLabels: true
+IndentPPDirectives: None
+IndentWidth: 4
+IndentWrappedFunctionNames: false
+KeepEmptyLinesAtTheStartOfBlocks: false
+MacroBlockBegin: ''
+MacroBlockEnd: ''
+MaxEmptyLinesToKeep: 1
+NamespaceIndentation: None
+PenaltyBreakAssignment: 2
+PenaltyBreakBeforeFirstCallParameter: 1
+PenaltyBreakComment: 300
+PenaltyBreakFirstLessLess: 120
+PenaltyBreakString: 1000
+PenaltyBreakTemplateDeclaration: 10
+PenaltyExcessCharacter: 1000000
+PenaltyReturnTypeOnItsOwnLine: 200
+PointerAlignment: Left
+RawStringFormats:
+  - Language: Cpp
+    Delimiters:
+      - cc
+      - CC
+      - cpp
+      - Cpp
+      - CPP
+      - 'c++'
+      - 'C++'
+    CanonicalDelimiter: ''
+    BasedOnStyle: google
+ReflowComments: true
+SortIncludes: true
+SortUsingDeclarations: true
+SpaceAfterCStyleCast: false
+SpaceAfterTemplateKeyword: true
+SpaceBeforeAssignmentOperators: true
+SpaceBeforeCpp11BracedList: false
+SpaceBeforeCtorInitializerColon: true
+SpaceBeforeInheritanceColon: true
+SpaceBeforeParens: ControlStatements
+SpaceBeforeRangeBasedForLoopColon: true
+SpaceInEmptyParentheses: false
+SpacesBeforeTrailingComments: 2
+SpacesInAngles: false
+SpacesInContainerLiterals: true
+SpacesInCStyleCastParentheses: false
+SpacesInParentheses: false
+SpacesInSquareBrackets: false
+Standard: Latest
+StatementMacros:
+  - Q_UNUSED
+  - QT_REQUIRE_VERSION
+TabWidth: 4
+UseTab: Never

.github/workflows/build.yml

@@ -92,7 +92,7 @@ jobs:
         include: ${{ fromJson(needs.prepare.outputs.variants) }}
     runs-on: ubuntu-latest
     container:
-      image: espressif/idf:release-v5.5
+      image: espressif/idf:v5.5.2
     steps:
       - name: Checkout
         uses: actions/checkout@v4

.gitignore

@@ -2,6 +2,7 @@ tmp/
 components/
 managed_components/
 build/
+dist/
 .vscode/
 .devcontainer/
 sdkconfig.old

CMakeLists.txt

@@ -1,14 +1,13 @@
-# For more information about build system see
-# https://docs.espressif.com/projects/esp-idf/en/latest/api-guides/build-system.html
-# The following five lines of boilerplate have to be in your project's
+# The following lines of boilerplate have to be in your project's
 # CMakeLists in this exact order for cmake to work correctly
 cmake_minimum_required(VERSION 3.16)
 
-set(PROJECT_VER "2.0.5")
-
 # Add this line to disable the specific warning
 add_compile_options(-Wno-missing-field-initializers)
 
 include($ENV{IDF_PATH}/tools/cmake/project.cmake)
-project(xiaozhi)
+# "Trim" the build. Include the minimal set of components, main, and anything it depends on.
+idf_build_set_property(MINIMAL_BUILD ON)
 
+set(PROJECT_VER "2.2.2")
+project(xiaozhi)

README.md

@@ -140,6 +140,7 @@ For server deployment on personal computers, refer to the following open-source
 - [xinnan-tech/xiaozhi-esp32-server](https://github.com/xinnan-tech/xiaozhi-esp32-server) Python server
 - [joey-zhou/xiaozhi-esp32-server-java](https://github.com/joey-zhou/xiaozhi-esp32-server-java) Java server
 - [AnimeAIChat/xiaozhi-server-go](https://github.com/AnimeAIChat/xiaozhi-server-go) Golang server
+- [hackers365/xiaozhi-esp32-server-golang](https://github.com/hackers365/xiaozhi-esp32-server-golang) Golang server
 
 Other client projects using the XiaoZhi communication protocol:
 
@@ -159,7 +160,7 @@ This is an open-source ESP32 project, released under the MIT license, allowing a
 
 We hope this project helps everyone understand AI hardware development and apply rapidly evolving large language models to real hardware devices.
 
-If you have any ideas or suggestions, please feel free to raise Issues or join the QQ group: 1011329060
+If you have any ideas or suggestions, please feel free to raise Issues or join our [Discord](https://discord.gg/bXqgAfRm) or QQ group: 994694848
 
 ## Star History
 

README_ja.md

@@ -140,6 +140,7 @@ Feishuドキュメントチュートリアルをご覧ください：
 - [xinnan-tech/xiaozhi-esp32-server](https://github.com/xinnan-tech/xiaozhi-esp32-server) Pythonサーバー
 - [joey-zhou/xiaozhi-esp32-server-java](https://github.com/joey-zhou/xiaozhi-esp32-server-java) Javaサーバー
 - [AnimeAIChat/xiaozhi-server-go](https://github.com/AnimeAIChat/xiaozhi-server-go) Golangサーバー
+- [hackers365/xiaozhi-esp32-server-golang](https://github.com/hackers365/xiaozhi-esp32-server-golang) Golangサーバー
 
 シャオジー通信プロトコルを利用した他のクライアントプロジェクト：
 
@@ -155,7 +156,7 @@ Feishuドキュメントチュートリアルをご覧ください：
 
 このプロジェクトを通じて、AIハードウェア開発を理解し、急速に進化する大規模言語モデルを実際のハードウェアデバイスに応用できるようになることを目指しています。
 
-ご意見やご提案があれば、いつでもIssueを提出するか、QQグループ：1011329060 にご参加ください。
+ご意見やご提案があれば、いつでもIssueを提出するか、[Discord](https://discord.gg/bXqgAfRm) または QQグループ：1011329060 にご参加ください。
 
 ## スター履歴
 

README_zh.md

@@ -140,6 +140,7 @@ v1 的稳定版本为 1.9.2，可以通过 `git checkout v1` 来切换到 v1 版
 - [xinnan-tech/xiaozhi-esp32-server](https://github.com/xinnan-tech/xiaozhi-esp32-server) Python 服务器
 - [joey-zhou/xiaozhi-esp32-server-java](https://github.com/joey-zhou/xiaozhi-esp32-server-java) Java 服务器
 - [AnimeAIChat/xiaozhi-server-go](https://github.com/AnimeAIChat/xiaozhi-server-go) Golang 服务器
+- [hackers365/xiaozhi-esp32-server-golang](https://github.com/hackers365/xiaozhi-esp32-server-golang) Golang 服务器
 
 使用小智通信协议的第三方客户端项目：
 
@@ -155,7 +156,7 @@ v1 的稳定版本为 1.9.2，可以通过 `git checkout v1` 来切换到 v1 版
 
 我们希望通过这个项目，能够帮助大家了解 AI 硬件开发，将当下飞速发展的大语言模型应用到实际的硬件设备中。
 
-如果你有任何想法或建议，请随时提出 Issues 或加入 QQ 群：1011329060
+如果你有任何想法或建议，请随时提出 Issues 或加入 [Discord](https://discord.gg/bXqgAfRm) 或 QQ 群：1011329060
 
 ## Star History
 

_codeql_detected_source_root

@@ -0,0 +1 @@
+.

docs/blufi.md

@@ -0,0 +1,37 @@
+# BluFi 配网（集成 esp-wifi-connect）
+
+本文档说明如何在小智固件中启用和使用 BluFi（BLE Wi‑Fi 配网），并结合项目内置的 `esp-wifi-connect` 组件完成 Wi‑Fi 连接与存储。官方
+BluFi
+协议说明请参考 [Espressif 文档](https://docs.espressif.com/projects/esp-idf/zh_CN/stable/esp32/api-guides/ble/blufi.html)。
+
+## 前置条件
+
+- 需要支持 BLE 的芯片与固件配置。
+- 在 `idf.py menuconfig` 中启用 `WiFi Configuration Method -> Esp Blufi`（`CONFIG_USE_ESP_BLUFI_WIFI_PROVISIONING=y`
+  ）。如果想使用 BluFi，必须关闭同一菜单下的 Hotspot 选项，否则默认使用 Hotspot 配网模式。
+
+- 保持默认的 NVS 与事件循环初始化（项目的 `app_main` 已处理）。
+- CONFIG_BT_BLUEDROID_ENABLED、CONFIG_BT_NIMBLE_ENABLED这两个宏应二选一，不能同时启用。
+## 工作流程
+
+1) 手机端通过 BluFi（如官方 EspBlufi App 或自研客户端）连接设备，发送 Wi‑Fi SSID/密码，手机端可以通过blufi协议获取设备端扫描到的WiFi列表。
+2) 设备侧在 `ESP_BLUFI_EVENT_REQ_CONNECT_TO_AP` 中将凭据写入 `SsidManager`（存储到 NVS，属于 `esp-wifi-connect` 组件）。
+3) 随后启动 `WifiStation` 扫描并连接；状态通过 BluFi 返回。
+4) 配网成功后设备会自动连接新 Wi‑Fi；失败则返回失败状态。
+
+## 使用步骤
+
+1. 配置：在 menuconfig 开启 `Esp Blufi`。编译并烧录固件。
+2. 触发配网：设备首次启动且没有已保存的 Wi‑Fi 时会自动进入配网。
+3. 手机端操作：打开 EspBlufi App（或其他 BluFi 客户端），搜索并连接设备，可以选择是否加密，按提示输入 Wi‑Fi SSID/密码并发送。
+4. 观察结果：
+    - 成功：BluFi 报告连接成功，设备自动连接 Wi‑Fi。
+    - 失败：BluFi 返回失败状态，可重新发送或检查路由器。
+
+## 注意事项
+
+- BluFi 配网不支持与热点配网同时开启。如果热点配网已经启动，则默认使用热点配网。请在 menuconfig 中只保留一种配网方式。
+- 若多次测试，建议清除或覆盖存储的 SSID（`wifi` 命名空间），避免旧配置干扰。
+- 如果使用自定义 BluFi 客户端，需遵循官方协议帧格式，参考上文官方文档链接。
+- 官方文档中已提供EspBlufi APP下载地址
+- 由于IDF5.5.2的blufi接口发生变化,5.5.2版本编译后蓝牙名称为"Xiaozhi-Blufi",5.5.1版本中蓝牙名称为"BLUFI_DEVICE"

docs/code_style.md

@@ -0,0 +1,91 @@
+# 代码风格指南
+
+## 代码格式化工具
+
+本项目使用 clang-format 工具来统一代码风格。我们已经在项目根目录下提供了 `.clang-format` 配置文件，该配置基于 Google C++ 风格指南，并做了一些自定义调整。
+
+### 安装 clang-format
+
+在使用之前，请确保你已经安装了 clang-format 工具：
+
+- **Windows**：
+  ```powershell
+  winget install LLVM
+  # 或者使用 Chocolatey
+  choco install llvm
+  ```
+
+- **Linux**：
+  ```bash
+  sudo apt install clang-format  # Ubuntu/Debian
+  sudo dnf install clang-tools-extra  # Fedora
+  ```
+
+- **macOS**：
+  ```bash
+  brew install clang-format
+  ```
+
+### 使用方法
+
+1. **格式化单个文件**：
+   ```bash
+   clang-format -i path/to/your/file.cpp
+   ```
+
+2. **格式化整个项目**：
+   ```bash
+   # 在项目根目录下执行
+   find main -iname *.h -o -iname *.cc | xargs clang-format -i
+   ```
+
+3. **在提交代码前检查格式**：
+   ```bash
+   # 检查文件格式是否符合规范（不修改文件）
+   clang-format --dry-run -Werror path/to/your/file.cpp
+   ```
+
+### IDE 集成
+
+- **Visual Studio Code**：
+  1. 安装 C/C++ 扩展
+  2. 在设置中启用 `C_Cpp.formatting` 为 `clang-format`
+  3. 可以设置保存时自动格式化：`editor.formatOnSave: true`
+
+- **CLion**：
+  1. 在设置中选择 `Editor > Code Style > C/C++`
+  2. 将 `Formatter` 设置为 `clang-format`
+  3. 选择使用项目中的 `.clang-format` 配置文件
+
+### 主要格式规则
+
+- 缩进使用 4 个空格
+- 行宽限制为 100 字符
+- 大括号采用 Attach 风格（与控制语句在同一行）
+- 指针和引用符号靠左对齐
+- 自动排序头文件包含
+- 类访问修饰符缩进为 -4 空格
+
+### 注意事项
+
+1. 提交代码前请确保代码已经过格式化
+2. 不要手动调整已格式化的代码对齐
+3. 如果某段代码不希望被格式化，可以使用以下注释包围：
+   ```cpp
+   // clang-format off
+   // 你的代码
+   // clang-format on
+   ```
+
+### 常见问题
+
+1. **格式化失败**：
+   - 检查 clang-format 版本是否过低
+   - 确认文件编码为 UTF-8
+   - 验证 .clang-format 文件语法是否正确
+
+2. **与期望格式不符**：
+   - 检查是否使用了项目根目录下的 .clang-format 配置
+   - 确认没有其他位置的 .clang-format 文件被优先使用
+
+如有任何问题或建议，欢迎提出 issue 或 pull request。

docs/custom-board.md

@@ -197,8 +197,9 @@ private:
     void InitializeButtons() {
         boot_button_.OnClick([this]() {
             auto& app = Application::GetInstance();
-            if (app.GetDeviceState() == kDeviceStateStarting && !WifiStation::GetInstance().IsConnected()) {
-                ResetWifiConfiguration();
+            if (app.GetDeviceState() == kDeviceStateStarting) {
+                EnterWifiConfigMode();
+                return;
             }
             app.ToggleChatState();
         });

main/CMakeLists.txt

@@ -33,7 +33,7 @@ set(SOURCES "audio/audio_codec.cc"
             "application.cc"
             "ota.cc"
             "settings.cc"
-            "device_state_event.cc"
+            "device_state_machine.cc"
             "assets.cc"
             "main.cc"
             )
@@ -41,10 +41,28 @@ set(SOURCES "audio/audio_codec.cc"
 set(INCLUDE_DIRS "." "display" "display/lvgl_display" "display/lvgl_display/jpg" "audio" "protocols")
 
 # Add board common files
-file(GLOB BOARD_COMMON_SOURCES ${CMAKE_CURRENT_SOURCE_DIR}/boards/common/*.cc)
-list(APPEND SOURCES ${BOARD_COMMON_SOURCES})
+list(APPEND SOURCES
+    "boards/common/board.cc"
+    "boards/common/wifi_board.cc"
+    "boards/common/ml307_board.cc"
+    "boards/common/nt26_board.cc"
+    "boards/common/dual_network_board.cc"
+    "boards/common/adc_battery_monitor.cc"
+    "boards/common/afsk_demod.cc"
+    "boards/common/axp2101.cc"
+    "boards/common/backlight.cc"
+    "boards/common/button.cc"
+    "boards/common/i2c_device.cc"
+    "boards/common/knob.cc"
+    "boards/common/power_save_timer.cc"
+    "boards/common/press_to_talk_mcp_tool.cc"
+    "boards/common/sleep_timer.cc"
+    "boards/common/sy6970.cc"
+    "boards/common/system_reset.cc"
+)
 list(APPEND INCLUDE_DIRS ${CMAKE_CURRENT_SOURCE_DIR}/boards/common)
 
+
 idf_build_get_property(build_components BUILD_COMPONENTS)
 # Function to find component dynamically by pattern
 function(find_component_by_pattern PATTERN COMPONENT_VAR PATH_VAR)
@@ -62,6 +80,8 @@ endfunction()
 set(BUILTIN_TEXT_FONT font_puhui_14_1)
 set(BUILTIN_ICON_FONT font_awesome_14_1)
 
+set(EMOTE_RESOLUTION "320_240")
+
 # Add board files according to BOARD_TYPE
 # Set default assets if the board uses partition table V2
 if(CONFIG_BOARD_TYPE_BREAD_COMPACT_WIFI)
@@ -72,6 +92,10 @@ elseif(CONFIG_BOARD_TYPE_BREAD_COMPACT_ML307)
     set(BOARD_TYPE "bread-compact-ml307")
     set(BUILTIN_TEXT_FONT font_puhui_basic_14_1)
     set(BUILTIN_ICON_FONT font_awesome_14_1)
+elseif(CONFIG_BOARD_TYPE_BREAD_COMPACT_NT26)
+    set(BOARD_TYPE "bread-compact-nt26")
+    set(BUILTIN_TEXT_FONT font_puhui_basic_14_1)
+    set(BUILTIN_ICON_FONT font_awesome_14_1)
 elseif(CONFIG_BOARD_TYPE_BREAD_COMPACT_ESP32)
     set(BOARD_TYPE "bread-compact-esp32")
 elseif(CONFIG_BOARD_TYPE_BREAD_COMPACT_ESP32_LCD)
@@ -80,26 +104,28 @@ elseif(CONFIG_BOARD_TYPE_BREAD_COMPACT_ESP32_LCD)
     set(BUILTIN_ICON_FONT font_awesome_14_1)
 elseif(CONFIG_BOARD_TYPE_DF_K10)
     set(BOARD_TYPE "df-k10")
-    set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
+    set(BUILTIN_TEXT_FONT font_noto_basic_20_4)
     set(BUILTIN_ICON_FONT font_awesome_20_4)
-    set(DEFAULT_EMOJI_COLLECTION twemoji_64)
+    set(DEFAULT_EMOJI_COLLECTION noto-emoji_128)
 elseif(CONFIG_BOARD_TYPE_DF_S3_AI_CAM)
     set(BOARD_TYPE "df-s3-ai-cam")
 elseif(CONFIG_BOARD_TYPE_ESP_BOX_3)
     set(BOARD_TYPE "esp-box-3")
-    set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
+    set(BUILTIN_TEXT_FONT font_noto_basic_20_4)
     set(BUILTIN_ICON_FONT font_awesome_20_4)
-    set(DEFAULT_EMOJI_COLLECTION twemoji_64)
+    set(DEFAULT_EMOJI_COLLECTION noto-emoji_128)
+    set(EMOTE_RESOLUTION "320_240")
 elseif(CONFIG_BOARD_TYPE_ESP_BOX)
     set(BOARD_TYPE "esp-box")
-    set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
+    set(BUILTIN_TEXT_FONT font_noto_basic_20_4)
     set(BUILTIN_ICON_FONT font_awesome_20_4)
-    set(DEFAULT_EMOJI_COLLECTION twemoji_64)
+    set(DEFAULT_EMOJI_COLLECTION noto-emoji_128)
+    set(EMOTE_RESOLUTION "320_240")
 elseif(CONFIG_BOARD_TYPE_ESP_BOX_LITE)
     set(BOARD_TYPE "esp-box-lite")
-    set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
+    set(BUILTIN_TEXT_FONT font_noto_basic_20_4)
     set(BUILTIN_ICON_FONT font_awesome_20_4)
-    set(DEFAULT_EMOJI_COLLECTION twemoji_64)
+    set(DEFAULT_EMOJI_COLLECTION noto-emoji_128)
 elseif(CONFIG_BOARD_TYPE_KEVIN_BOX_2)
     set(BOARD_TYPE "kevin-box-2")
     set(BUILTIN_TEXT_FONT font_puhui_basic_14_1)
@@ -108,14 +134,14 @@ elseif(CONFIG_BOARD_TYPE_KEVIN_C3)
     set(BOARD_TYPE "kevin-c3")
 elseif(CONFIG_BOARD_TYPE_KEVIN_SP_V3_DEV)
     set(BOARD_TYPE "kevin-sp-v3-dev")
-    set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
+    set(BUILTIN_TEXT_FONT font_noto_basic_20_4)
     set(BUILTIN_ICON_FONT font_awesome_20_4)
-    set(DEFAULT_EMOJI_COLLECTION twemoji_64)
+    set(DEFAULT_EMOJI_COLLECTION noto-emoji_128)
 elseif(CONFIG_BOARD_TYPE_KEVIN_SP_V4_DEV)
     set(BOARD_TYPE "kevin-sp-v4-dev")
-    set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
+    set(BUILTIN_TEXT_FONT font_noto_basic_20_4)
     set(BUILTIN_ICON_FONT font_awesome_20_4)
-    set(DEFAULT_EMOJI_COLLECTION twemoji_64)
+    set(DEFAULT_EMOJI_COLLECTION noto-emoji_128)
 elseif(CONFIG_BOARD_TYPE_KEVIN_YUYING_313LCD)
     set(BOARD_TYPE "kevin-yuying-313lcd")
     set(BUILTIN_TEXT_FONT font_puhui_basic_30_4)
@@ -123,9 +149,9 @@ elseif(CONFIG_BOARD_TYPE_KEVIN_YUYING_313LCD)
     set(DEFAULT_EMOJI_COLLECTION twemoji_64)
 elseif(CONFIG_BOARD_TYPE_LICHUANG_DEV_S3)
     set(BOARD_TYPE "lichuang-dev")
-    set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
+    set(BUILTIN_TEXT_FONT font_noto_basic_20_4)
     set(BUILTIN_ICON_FONT font_awesome_20_4)
-    set(DEFAULT_EMOJI_COLLECTION twemoji_64)
+    set(DEFAULT_EMOJI_COLLECTION noto-emoji_128)
 elseif(CONFIG_BOARD_TYPE_LICHUANG_DEV_C3)
     set(BOARD_TYPE "lichuang-c3-dev")
     set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
@@ -175,6 +201,11 @@ elseif(CONFIG_BOARD_TYPE_M5STACK_ATOM_S3R_CAM_M12_ECHO_BASE)
     set(BOARD_TYPE "atoms3r-cam-m12-echo-base")
 elseif(CONFIG_BOARD_TYPE_M5STACK_ATOM_ECHOS3R)
     set(BOARD_TYPE "atom-echos3r")
+elseif(CONFIG_BOARD_TYPE_M5STACK_CARDPUTER_ADV)
+    set(BOARD_TYPE "m5stack-cardputer-adv")
+    set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
+    set(BUILTIN_ICON_FONT font_awesome_20_4)
+    set(DEFAULT_EMOJI_COLLECTION twemoji_32)
 elseif(CONFIG_BOARD_TYPE_M5STACK_ATOM_MATRIX_ECHO_BASE)
     set(BOARD_TYPE "atommatrix-echo-base")
 elseif(CONFIG_BOARD_TYPE_XMINI_C3_V3)
@@ -194,13 +225,20 @@ elseif(CONFIG_BOARD_TYPE_ESP_KORVO2_V3)
     set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
     set(BUILTIN_ICON_FONT font_awesome_20_4)
     set(DEFAULT_EMOJI_COLLECTION twemoji_64)
+elseif(CONFIG_BOARD_TYPE_ESP_KORVO2_V3_RNDIS)
+    set(BOARD_TYPE "esp32s3-korvo2-v3-rndis")
+    set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
+    set(BUILTIN_ICON_FONT font_awesome_20_4)
+    set(DEFAULT_EMOJI_COLLECTION twemoji_64)
 elseif(CONFIG_BOARD_TYPE_ESP_SPARKBOT)
     set(BOARD_TYPE "esp-sparkbot")
     set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
     set(BUILTIN_ICON_FONT font_awesome_20_4)
     set(DEFAULT_EMOJI_COLLECTION twemoji_64)
 elseif(CONFIG_BOARD_TYPE_ESP_SPOT_S3)
-    set(BOARD_TYPE "esp-spot-s3")
+    set(BOARD_TYPE "esp-spot")
+elseif(CONFIG_BOARD_TYPE_ESP_SPOT_C5)
+    set(BOARD_TYPE "esp-spot")
 elseif(CONFIG_BOARD_TYPE_ESP_HI)
     set(BOARD_TYPE "esp-hi")
     # Set ESP_HI emoji directory for DEFAULT_ASSETS_EXTRA_FILES
@@ -210,6 +248,13 @@ elseif(CONFIG_BOARD_TYPE_ECHOEAR)
     set(BUILTIN_TEXT_FONT font_puhui_20_4)
     set(BUILTIN_ICON_FONT font_awesome_20_4)
     set(DEFAULT_EMOJI_COLLECTION twemoji_64)
+    set(EMOTE_RESOLUTION "360_360")
+    # set(EMOTE_EXTERNAL_PATH "${CMAKE_CURRENT_SOURCE_DIR}/boards/echoear/assets")
+elseif(CONFIG_BOARD_TYPE_ESP_SENSAIRSHUTTLE)
+    set(BOARD_TYPE "esp-sensairshuttle")
+    set(BUILTIN_TEXT_FONT font_puhui_basic_16_4)
+    set(BUILTIN_ICON_FONT font_awesome_16_4)
+    set(DEFAULT_EMOJI_COLLECTION twemoji_32)
 elseif(CONFIG_BOARD_TYPE_WAVESHARE_S3_AUDIO_BOARD)
     set(BOARD_TYPE "waveshare-s3-audio-board")
     set(BUILTIN_TEXT_FONT font_puhui_basic_16_4)
@@ -220,6 +265,11 @@ elseif(CONFIG_BOARD_TYPE_WAVESHARE_S3_TOUCH_AMOLED_1_8)
     set(BUILTIN_TEXT_FONT font_puhui_basic_30_4)
     set(BUILTIN_ICON_FONT font_awesome_30_4)
     set(DEFAULT_EMOJI_COLLECTION twemoji_64)
+elseif(CONFIG_BOARD_TYPE_WAVESHARE_C6_TOUCH_AMOLED_1_8)
+    set(BOARD_TYPE "waveshare-c6-touch-amoled-1.8")
+    set(BUILTIN_TEXT_FONT font_puhui_basic_30_4)
+    set(BUILTIN_ICON_FONT font_awesome_30_4)
+    set(DEFAULT_EMOJI_COLLECTION twemoji_64)
 elseif(CONFIG_BOARD_TYPE_WAVESHARE_S3_TOUCH_AMOLED_2_06)
     set(BOARD_TYPE "waveshare-s3-touch-amoled-2.06")
     set(BUILTIN_TEXT_FONT font_puhui_basic_30_4)
@@ -235,6 +285,11 @@ elseif(CONFIG_BOARD_TYPE_WAVESHARE_S3_TOUCH_LCD_4B)
     set(BUILTIN_TEXT_FONT font_puhui_basic_30_4)
     set(BUILTIN_ICON_FONT font_awesome_30_4)
     set(DEFAULT_EMOJI_COLLECTION twemoji_64)
+elseif(CONFIG_BOARD_TYPE_WAVESHARE_S3_TOUCH_LCD_4_3C)
+    set(BOARD_TYPE "waveshare-s3-touch-lcd-4.3c")
+    set(BUILTIN_TEXT_FONT font_puhui_basic_30_4)
+    set(BUILTIN_ICON_FONT font_awesome_30_4)
+    set(DEFAULT_EMOJI_COLLECTION twemoji_64)
 elseif(CONFIG_BOARD_TYPE_WAVESHARE_S3_TOUCH_AMOLED_1_75)
     set(BOARD_TYPE "waveshare-s3-touch-amoled-1.75")
     set(BUILTIN_TEXT_FONT font_puhui_basic_30_4)
@@ -274,6 +329,10 @@ elseif(CONFIG_BOARD_TYPE_WAVESHARE_S3_ePaper_1_54)
     set(BOARD_TYPE "waveshare-s3-epaper-1.54")
     set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
     set(BUILTIN_ICON_FONT font_awesome_20_4)
+elseif(CONFIG_BOARD_TYPE_WAVESHARE_S3_RLCD_4_2)
+    set(BOARD_TYPE "waveshare-s3-rlcd-4.2")
+    set(BUILTIN_TEXT_FONT font_puhui_basic_30_4)
+    set(BUILTIN_ICON_FONT font_awesome_30_4)
 elseif(CONFIG_BOARD_TYPE_WAVESHARE_S3_TOUCH_LCD_3_49)
     set(BOARD_TYPE "waveshare-s3-touch-lcd-3.49")
     set(LVGL_TEXT_FONT font_puhui_basic_30_4)
@@ -284,6 +343,11 @@ elseif(CONFIG_BOARD_TYPE_WAVESHARE_C6_LCD_1_69)
     set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
     set(BUILTIN_ICON_FONT font_awesome_20_4)
     set(DEFAULT_EMOJI_COLLECTION twemoji_64)
+elseif(CONFIG_BOARD_TYPE_WAVESHARE_C6_TOUCH_LCD_1_83)
+    set(BOARD_TYPE "waveshare-c6-touch-lcd-1.83")
+    set(BUILTIN_TEXT_FONT font_puhui_basic_16_4)
+    set(BUILTIN_ICON_FONT font_awesome_16_4)
+    set(DEFAULT_EMOJI_COLLECTION twemoji_64)
 elseif(CONFIG_BOARD_TYPE_WAVESHARE_C6_TOUCH_AMOLED_1_43)
     set(BOARD_TYPE "waveshare-c6-touch-amoled-1.43")
     set(BUILTIN_TEXT_FONT font_puhui_basic_30_4)
@@ -365,6 +429,11 @@ elseif(CONFIG_BOARD_TYPE_MOVECALL_MOJI_ESP32S3)
     set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
     set(BUILTIN_ICON_FONT font_awesome_20_4)
     set(DEFAULT_EMOJI_COLLECTION twemoji_64)
+elseif(CONFIG_BOARD_TYPE_MOVECALL_MOJI2_ESP32C5)
+    set(BOARD_TYPE "movecall-moji2-esp32c5")
+    set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
+    set(BUILTIN_ICON_FONT font_awesome_20_4)
+    set(DEFAULT_EMOJI_COLLECTION twemoji_64)
 elseif(CONFIG_BOARD_TYPE_MOVECALL_CUICAN_ESP32S3)
     set(BOARD_TYPE "movecall-cuican-esp32s3")
     set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
@@ -372,29 +441,29 @@ elseif(CONFIG_BOARD_TYPE_MOVECALL_CUICAN_ESP32S3)
     set(DEFAULT_EMOJI_COLLECTION twemoji_64)
 elseif(CONFIG_BOARD_TYPE_ATK_DNESP32S3)
     set(BOARD_TYPE "atk-dnesp32s3")
-    set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
+    set(BUILTIN_TEXT_FONT font_noto_basic_20_4)
     set(BUILTIN_ICON_FONT font_awesome_20_4)
-    set(DEFAULT_EMOJI_COLLECTION twemoji_64)
+    set(DEFAULT_EMOJI_COLLECTION noto-emoji_128)
 elseif(CONFIG_BOARD_TYPE_ATK_DNESP32S3_BOX)
     set(BOARD_TYPE "atk-dnesp32s3-box")
-    set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
+    set(BUILTIN_TEXT_FONT font_noto_basic_20_4)
     set(BUILTIN_ICON_FONT font_awesome_20_4)
-    set(DEFAULT_EMOJI_COLLECTION twemoji_64)
+    set(DEFAULT_EMOJI_COLLECTION noto-emoji_128)
 elseif(CONFIG_BOARD_TYPE_ATK_DNESP32S3_BOX0)
     set(BOARD_TYPE "atk-dnesp32s3-box0")
-    set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
+    set(BUILTIN_TEXT_FONT font_noto_basic_20_4)
     set(BUILTIN_ICON_FONT font_awesome_20_4)
-    set(DEFAULT_EMOJI_COLLECTION twemoji_64)
+    set(DEFAULT_EMOJI_COLLECTION noto-emoji_128)
 elseif(CONFIG_BOARD_TYPE_ATK_DNESP32S3_BOX2_WIFI)
     set(BOARD_TYPE "atk-dnesp32s3-box2-wifi")
-    set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
+    set(BUILTIN_TEXT_FONT font_noto_basic_20_4)
     set(BUILTIN_ICON_FONT font_awesome_20_4)
-    set(DEFAULT_EMOJI_COLLECTION twemoji_64)
+    set(DEFAULT_EMOJI_COLLECTION noto-emoji_128)
 elseif(CONFIG_BOARD_TYPE_ATK_DNESP32S3_BOX2_4G)
     set(BOARD_TYPE "atk-dnesp32s3-box2-4g")
-    set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
+    set(BUILTIN_TEXT_FONT font_noto_basic_20_4)
     set(BUILTIN_ICON_FONT font_awesome_20_4)
-    set(DEFAULT_EMOJI_COLLECTION twemoji_64)
+    set(DEFAULT_EMOJI_COLLECTION noto-emoji_128)
 elseif(CONFIG_BOARD_TYPE_ATK_DNESP32S3M_WIFI)
     set(BOARD_TYPE "atk-dnesp32s3m-wifi")
     set(BUILTIN_TEXT_FONT font_puhui_basic_16_4)
@@ -435,19 +504,24 @@ elseif(CONFIG_BOARD_TYPE_XINGZHI_CUBE_0_96OLED_ML307)
     set(BUILTIN_ICON_FONT font_awesome_14_1)
 elseif(CONFIG_BOARD_TYPE_XINGZHI_CUBE_1_54TFT_WIFI)
     set(BOARD_TYPE "xingzhi-cube-1.54tft-wifi")
-    set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
+    set(BUILTIN_TEXT_FONT font_noto_basic_20_4)
     set(BUILTIN_ICON_FONT font_awesome_20_4)
-    set(DEFAULT_EMOJI_COLLECTION twemoji_64)
+    set(DEFAULT_EMOJI_COLLECTION noto-emoji_128)
 elseif(CONFIG_BOARD_TYPE_XINGZHI_CUBE_1_54TFT_ML307)
     set(BOARD_TYPE "xingzhi-cube-1.54tft-ml307")
-    set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
+    set(BUILTIN_TEXT_FONT font_noto_basic_20_4)
     set(BUILTIN_ICON_FONT font_awesome_20_4)
-    set(DEFAULT_EMOJI_COLLECTION twemoji_64)
+    set(DEFAULT_EMOJI_COLLECTION noto-emoji_128)
+elseif(CONFIG_BOARD_TYPE_XINGZHI_METAL_1_54_WIFI)
+    set(BOARD_TYPE "xingzhi-metal-1.54-wifi")
+    set(BUILTIN_TEXT_FONT font_noto_basic_20_4)
+    set(BUILTIN_ICON_FONT font_awesome_20_4)
+    set(DEFAULT_EMOJI_COLLECTION noto-emoji_128)  
 elseif(CONFIG_BOARD_TYPE_SEEED_STUDIO_SENSECAP_WATCHER)
     set(BOARD_TYPE "sensecap-watcher")
-    set(BUILTIN_TEXT_FONT font_puhui_basic_30_4)
+    set(BUILTIN_TEXT_FONT font_noto_basic_30_4)
     set(BUILTIN_ICON_FONT font_awesome_20_4)
-    set(DEFAULT_EMOJI_COLLECTION twemoji_64)
+    set(DEFAULT_EMOJI_COLLECTION noto-emoji_128)
 elseif(CONFIG_BOARD_TYPE_DOIT_S3_AIBOX)
     set(BOARD_TYPE "doit-s3-aibox")
 elseif(CONFIG_BOARD_TYPE_MIXGO_NOVA)
@@ -493,6 +567,16 @@ elseif(CONFIG_BOARD_TYPE_ZHENGCHEN_1_54TFT_ML307)
     set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
     set(BUILTIN_ICON_FONT font_awesome_20_4)
     set(DEFAULT_EMOJI_COLLECTION twemoji_64)
+elseif(CONFIG_BOARD_TYPE_ZHENGCHEN_CAM)
+    set(BOARD_TYPE "zhengchen-cam")
+    set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
+    set(BUILTIN_ICON_FONT font_awesome_20_4)
+    set(DEFAULT_EMOJI_COLLECTION twemoji_64)
+elseif(CONFIG_BOARD_TYPE_ZHENGCHEN_CAM_ML307)
+    set(BOARD_TYPE "zhengchen-cam-ml307")
+    set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)
+    set(BUILTIN_ICON_FONT font_awesome_20_4)
+    set(DEFAULT_EMOJI_COLLECTION twemoji_64)    
 elseif(CONFIG_BOARD_TYPE_SPOTPEAR_ESP32_S3_1_54_MUMA)
     set(BOARD_TYPE "sp-esp32-s3-1.54-muma")
     set(BUILTIN_TEXT_FONT font_puhui_basic_16_4)
@@ -507,10 +591,12 @@ elseif(CONFIG_BOARD_TYPE_OTTO_ROBOT)
     set(BOARD_TYPE "otto-robot")
     set(BUILTIN_TEXT_FONT font_puhui_16_4)
     set(BUILTIN_ICON_FONT font_awesome_16_4)
+    set(DEFAULT_EMOJI_COLLECTION otto-gif)
 elseif(CONFIG_BOARD_TYPE_ELECTRON_BOT)
     set(BOARD_TYPE "electron-bot")
     set(BUILTIN_TEXT_FONT font_puhui_20_4)
     set(BUILTIN_ICON_FONT font_awesome_20_4)
+    set(DEFAULT_EMOJI_COLLECTION otto-gif)
 elseif(CONFIG_BOARD_TYPE_BREAD_COMPACT_WIFI_CAM)
     set(BOARD_TYPE "bread-compact-wifi-s3cam")
     set(BUILTIN_TEXT_FONT font_puhui_basic_16_4)
@@ -551,6 +637,10 @@ elseif(CONFIG_BOARD_TYPE_AIPI_LITE)
     set(BUILTIN_TEXT_FONT font_puhui_basic_14_1)
     set(BUILTIN_ICON_FONT font_awesome_14_1)
     set(DEFAULT_EMOJI_COLLECTION twemoji_32)
+elseif(CONFIG_BOARD_TYPE_HU_087)
+    set(BOARD_TYPE "hu-087")
+    set(BUILTIN_TEXT_FONT font_puhui_basic_14_1)
+    set(BUILTIN_ICON_FONT font_awesome_14_1)
 endif()
 
 file(GLOB BOARD_SOURCES
@@ -572,6 +662,10 @@ else()
     list(APPEND SOURCES "audio/wake_words/esp_wake_word.cc")
 endif()
 
+# Auto Select Additional Sources
+if (CONFIG_USE_ESP_BLUFI_WIFI_PROVISIONING)
+    list(APPEND SOURCES "boards/common/blufi.cpp")
+endif ()
 # Select language directory according to Kconfig
 if(CONFIG_LANGUAGE_ZH_CN)
     set(LANG_DIR "zh-CN")
@@ -687,16 +781,47 @@ if(CONFIG_IDF_TARGET_ESP32)
                              "audio/codecs/es8388_audio_codec.cc"
                              "audio/codecs/es8389_audio_codec.cc"
                              "led/gpio_led.cc"
-                             "${CMAKE_CURRENT_SOURCE_DIR}/boards/common/esp32_camera.cc"
                              "display/lvgl_display/jpg/image_to_jpeg.cpp"
                              "display/lvgl_display/jpg/jpeg_to_image.c"
+                             "boards/common/nt26_board.cc"
+                             "boards/common/ml307_board.cc"
+                             "boards/common/dual_network_board.cc"
                              )
 endif()
 
+# Include EspVideo if target is ESP32S3 or ESP32P4
+if(CONFIG_IDF_TARGET_ESP32S3 OR CONFIG_IDF_TARGET_ESP32P4)
+    list(APPEND SOURCES "boards/common/esp_video.cc"
+                        "boards/common/rndis_board.cc"
+                        )
+endif()
+
+# Include Esp32Camera if target is ESP32S3
+if(CONFIG_IDF_TARGET_ESP32S3)
+    list(APPEND SOURCES "boards/common/esp32_camera.cc")
+endif()
+
 idf_component_register(SRCS ${SOURCES}
                     EMBED_FILES ${LANG_SOUNDS} ${COMMON_SOUNDS}
                     INCLUDE_DIRS ${INCLUDE_DIRS}
                     WHOLE_ARCHIVE
+                    PRIV_REQUIRES
+                        esp_pm
+                        esp_psram
+                        esp_netif
+                        esp_driver_gpio
+                        esp_driver_uart
+                        esp_driver_spi
+                        esp_driver_i2c
+                        esp_driver_i2s
+                        esp_driver_jpeg
+                        esp_driver_ppa
+                        esp_app_format
+                        app_update
+                        spi_flash
+                        console
+                        efuse
+                        bt
                     )
 
 # Use target_compile_definitions to define BOARD_TYPE, BOARD_NAME
@@ -898,6 +1023,14 @@ if ("${size}" AND "${offset}")
         get_assets_local_file("${CONFIG_CUSTOM_ASSETS_FILE}" ASSETS_LOCAL_FILE)
         esptool_py_flash_to_partition(flash "assets" "${ASSETS_LOCAL_FILE}")
         message(STATUS "Custom assets flash configured: ${ASSETS_LOCAL_FILE} -> assets partition")
+    elseif(CONFIG_FLASH_EXPRESSION_ASSETS)
+        set(ASSETS_NAME "expression_assets")
+        set(ASSETS_PARTITION "assets")
+        set(ASSETS_FILE "${CMAKE_BINARY_DIR}/${ASSETS_NAME}.bin")
+
+        build_speaker_assets_bin("${ASSETS_PARTITION}" ${EMOTE_RESOLUTION} ${ASSETS_FILE} ${CONFIG_MMAP_FILE_NAME_LENGTH})
+        message(STATUS "Generated emote assets: ${ASSETS_FILE} -> ${ASSETS_PARTITION} partition")
+        esptool_py_flash_to_partition(flash "${ASSETS_PARTITION}" "${ASSETS_FILE}")
     elseif(CONFIG_FLASH_NONE_ASSETS)
         message(STATUS "Assets flashing disabled (FLASH_NONE_ASSETS)")
     endif()

main/Kconfig.projbuild

@@ -8,7 +8,8 @@ config OTA_URL
 
 choice
     prompt "Flash Assets"
-    default FLASH_DEFAULT_ASSETS
+    default FLASH_DEFAULT_ASSETS if !USE_EMOTE_MESSAGE_STYLE
+    default FLASH_EXPRESSION_ASSETS if USE_EMOTE_MESSAGE_STYLE
     help
         Select the assets to flash.
 
@@ -16,8 +17,12 @@ choice
         bool "Do not flash assets"
     config FLASH_DEFAULT_ASSETS
         bool "Flash Default Assets"
+        depends on !USE_EMOTE_MESSAGE_STYLE
     config FLASH_CUSTOM_ASSETS
         bool "Flash Custom Assets"
+    config FLASH_EXPRESSION_ASSETS
+        bool "Flash Emote Assets"
+        depends on USE_EMOTE_MESSAGE_STYLE
 endchoice
 
 config CUSTOM_ASSETS_FILE
@@ -129,6 +134,9 @@ choice BOARD_TYPE
     config BOARD_TYPE_BREAD_COMPACT_ML307
         bool "Bread Compact ML307/EC801E (面包板 4G)"
         depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_BREAD_COMPACT_NT26
+        bool "Bread Compact NT26 (面包板 4G)"
+        depends on IDF_TARGET_ESP32S3
     config BOARD_TYPE_BREAD_COMPACT_ESP32
         bool "Bread Compact ESP32 DevKit (面包板)"
         depends on IDF_TARGET_ESP32
@@ -147,12 +155,21 @@ choice BOARD_TYPE
     config BOARD_TYPE_ESP_KORVO2_V3
         bool "Espressif Korvo2 V3"
         depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_ESP_KORVO2_V3_RNDIS
+        bool "Espressif Korvo2 V3 RNDIS"
+        depends on IDF_TARGET_ESP32S3
     config BOARD_TYPE_ESP_SPARKBOT
         bool "Espressif SparkBot"
         depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_ESP_SENSAIRSHUTTLE
+        bool "Espressif ESP-SensairShuttle"
+        depends on IDF_TARGET_ESP32C5
     config BOARD_TYPE_ESP_SPOT_S3
         bool "Espressif Spot-S3"
         depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_ESP_SPOT_C5
+        bool "Espressif Spot-C5"
+        depends on IDF_TARGET_ESP32C5
     config BOARD_TYPE_ESP_HI
         bool "Espressif ESP-HI"
         depends on IDF_TARGET_ESP32C3
@@ -234,6 +251,9 @@ choice BOARD_TYPE
     config BOARD_TYPE_M5STACK_ATOM_ECHOS3R
         bool "M5Stack AtomEchoS3R"
         depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_M5STACK_CARDPUTER_ADV
+        bool "M5Stack Cardputer Adv"
+        depends on IDF_TARGET_ESP32S3
     config BOARD_TYPE_M5STACK_ATOM_MATRIX_ECHO_BASE
         bool "M5Stack AtomMatrix + Echo Base"
         depends on IDF_TARGET_ESP32
@@ -258,6 +278,9 @@ choice BOARD_TYPE
     config BOARD_TYPE_WAVESHARE_S3_TOUCH_LCD_4B
         bool "Waveshare ESP32-S3-Touch-LCD-4B"
         depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_WAVESHARE_S3_TOUCH_LCD_4_3C
+        bool "Waveshare ESP32-S3-Touch-LCD-4.3C"
+        depends on IDF_TARGET_ESP32S3
     config BOARD_TYPE_WAVESHARE_S3_TOUCH_LCD_1_85C
         bool "Waveshare ESP32-S3-Touch-LCD-1.85C"
         depends on IDF_TARGET_ESP32S3
@@ -270,12 +293,18 @@ choice BOARD_TYPE
     config BOARD_TYPE_WAVESHARE_C6_LCD_1_69
         bool "Waveshare ESP32-C6-LCD-1.69"
         depends on IDF_TARGET_ESP32C6
+    config BOARD_TYPE_WAVESHARE_C6_TOUCH_LCD_1_83
+        bool "Waveshare ESP32-C6-Touch-LCD-1.83"
+        depends on IDF_TARGET_ESP32C6
     config BOARD_TYPE_WAVESHARE_C6_TOUCH_AMOLED_1_43
         bool "Waveshare ESP32-C6-Touch-AMOLOED-1.43"
         depends on IDF_TARGET_ESP32C6
     config BOARD_TYPE_WAVESHARE_C6_TOUCH_AMOLED_1_32
         bool "Waveshare ESP32-C6-Touch-AMOLOED-1.32"
         depends on IDF_TARGET_ESP32C6
+    config BOARD_TYPE_WAVESHARE_C6_TOUCH_AMOLED_1_8
+        bool "Waveshare ESP32-C6-Touch-AMOLED-1.8"
+        depends on IDF_TARGET_ESP32C6
     config BOARD_TYPE_WAVESHARE_S3_TOUCH_AMOLED_1_32
         bool "Waveshare ESP32-S3-Touch-AMOLOED-1.32"
         depends on IDF_TARGET_ESP32S3
@@ -288,6 +317,9 @@ choice BOARD_TYPE
     config BOARD_TYPE_WAVESHARE_S3_ePaper_1_54
         bool "Waveshare ESP32-S3-ePaper-1.54"
         depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_WAVESHARE_S3_RLCD_4_2
+        bool "Waveshare ESP32-S3-RLCD-4.2"
+        depends on IDF_TARGET_ESP32S3
     config BOARD_TYPE_WAVESHARE_S3_TOUCH_LCD_3_5B
         bool "Waveshare ESP32-S3-Touch-LCD-3.5B"
         depends on IDF_TARGET_ESP32S3
@@ -327,6 +359,9 @@ choice BOARD_TYPE
     config BOARD_TYPE_MOVECALL_MOJI_ESP32S3
         bool "Movecall Moji 小智AI衍生版"
         depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_MOVECALL_MOJI2_ESP32C5
+        bool "Movecall Moji2.0 小智AI衍生版"
+        depends on IDF_TARGET_ESP32C5
     config BOARD_TYPE_MOVECALL_CUICAN_ESP32S3
         bool "Movecall CuiCan 璀璨·AI吊坠"
         depends on IDF_TARGET_ESP32S3
@@ -375,6 +410,9 @@ choice BOARD_TYPE
     config BOARD_TYPE_XINGZHI_CUBE_1_54TFT_ML307
         bool "无名科技星智1.54(ML307)"
         depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_XINGZHI_METAL_1_54_WIFI
+        bool "无名科技星智1.54 METAL(wifi)"
+        depends on IDF_TARGET_ESP32S3
     config BOARD_TYPE_SEEED_STUDIO_SENSECAP_WATCHER
         bool "Seeed Studio SenseCAP Watcher"
         depends on IDF_TARGET_ESP32S3
@@ -399,6 +437,12 @@ choice BOARD_TYPE
     config BOARD_TYPE_ZHENGCHEN_1_54TFT_ML307
         bool "征辰科技1.54(ML307)"
         depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_ZHENGCHEN_CAM
+        bool "征辰科技AI Camera"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_ZHENGCHEN_CAM_ML307
+        bool "征辰科技AI Camera(ML307)"
+	depends on IDF_TARGET_ESP32S3
     config BOARD_TYPE_MINSI_K08_DUAL
         bool "敏思科技K08(DUAL)"
         depends on IDF_TARGET_ESP32S3
@@ -435,6 +479,9 @@ choice BOARD_TYPE
     config BOARD_TYPE_AIPI_LITE
         bool "AIPI-Lite"
         depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_HU_087
+        bool "HU-087"
+        depends on IDF_TARGET_ESP32S3
 endchoice
 
 choice
@@ -468,7 +515,7 @@ choice ESP_S3_LCD_EV_Board_Version_TYPE
 endchoice
 
 choice DISPLAY_OLED_TYPE
-    depends on BOARD_TYPE_BREAD_COMPACT_WIFI || BOARD_TYPE_BREAD_COMPACT_ML307 || BOARD_TYPE_BREAD_COMPACT_ESP32
+    depends on BOARD_TYPE_BREAD_COMPACT_WIFI || BOARD_TYPE_BREAD_COMPACT_ML307 || BOARD_TYPE_BREAD_COMPACT_NT26 || BOARD_TYPE_BREAD_COMPACT_ESP32 || BOARD_TYPE_HU_087
     prompt "OLED Type"
     default OLED_SSD1306_128X32
     help
@@ -530,7 +577,7 @@ choice DISPLAY_LCD_TYPE
 endchoice
 
 choice DISPLAY_ESP32S3_KORVO2_V3
-    depends on BOARD_TYPE_ESP_KORVO2_V3
+    depends on BOARD_TYPE_ESP_KORVO2_V3 || BOARD_TYPE_ESP_KORVO2_V3_RNDIS
     prompt "ESP32S3_KORVO2_V3 LCD Type"
     default ESP32S3_KORVO2_V3_LCD_ST7789
     help
@@ -567,7 +614,9 @@ choice DISPLAY_STYLE
 
     config USE_EMOTE_MESSAGE_STYLE
         bool "Emote animation style"
-        depends on BOARD_TYPE_ESP_BOX_3 || BOARD_TYPE_ECHOEAR || BOARD_TYPE_LICHUANG_DEV_S3
+        depends on BOARD_TYPE_ESP_BOX || BOARD_TYPE_ESP_BOX_3 \
+            || BOARD_TYPE_ECHOEAR || BOARD_TYPE_LICHUANG_DEV_S3 \
+            || BOARD_TYPE_ESP_SENSAIRSHUTTLE
 endchoice
 
 choice WAKE_WORD_TYPE
@@ -631,6 +680,16 @@ config SEND_WAKE_WORD_DATA
     help
         Send wake word data to the server as the first message of the conversation and wait for response
 
+config WAKE_WORD_DETECTION_IN_LISTENING
+    bool "Enable Wake Word Detection in Listening Mode"
+    default n
+    depends on USE_AFE_WAKE_WORD || USE_CUSTOM_WAKE_WORD
+    help
+        Enable wake word detection while in listening mode.
+        When enabled, the device can detect wake word during listening,
+        which allows interrupting the current conversation.
+        When disabled (default), wake word detection is turned off during listening.
+
 config USE_AUDIO_PROCESSOR
     bool "Enable Audio Noise Reduction"
     default y
@@ -645,7 +704,8 @@ config USE_DEVICE_AEC
         || BOARD_TYPE_LICHUANG_DEV_S3 || BOARD_TYPE_ESP_KORVO2_V3 || BOARD_TYPE_WAVESHARE_S3_TOUCH_AMOLED_1_75 || BOARD_TYPE_WAVESHARE_S3_TOUCH_LCD_1_83\
         || BOARD_TYPE_WAVESHARE_S3_TOUCH_AMOLED_2_06 || BOARD_TYPE_WAVESHARE_S3_TOUCH_LCD_4B || BOARD_TYPE_WAVESHARE_P4_WIFI6_TOUCH_LCD_4B || BOARD_TYPE_WAVESHARE_P4_WIFI6_TOUCH_LCD_7B \
         || BOARD_TYPE_WAVESHARE_P4_WIFI6_TOUCH_LCD_XC || BOARD_TYPE_ESP_S3_LCD_EV_Board_2 || BOARD_TYPE_YUNLIAO_S3 \
-        || BOARD_TYPE_ECHOEAR || BOARD_TYPE_WAVESHARE_S3_TOUCH_LCD_3_49)
+        || BOARD_TYPE_ECHOEAR || BOARD_TYPE_WAVESHARE_S3_TOUCH_LCD_3_49 || BOARD_TYPE_WAVESHARE_S3_RLCD_4_2 || BOARD_TYPE_ZHENGCHEN_CAM || BOARD_TYPE_ZHENGCHEN_CAM_ML307 \
+        || BOARD_TYPE_WAVESHARE_S3_TOUCH_LCD_4_3C)
     help
         To work properly, device-side AEC requires a clean output reference path from the speaker signal and physical acoustic isolation between the microphone and speaker.
 
@@ -662,6 +722,29 @@ config USE_AUDIO_DEBUGGER
     help
         Enable audio debugger, send audio data through UDP to the host machine
 
+menu "WiFi Configuration Method"
+    help
+        WiFi Configuration Method Selection
+    config USE_HOTSPOT_WIFI_PROVISIONING
+        bool "Hotspot"
+        default y
+        help
+            Use WiFi Hotspot to transmit WiFi configuration data
+    config USE_ACOUSTIC_WIFI_PROVISIONING
+        bool "Acoustic"
+        help
+            Use audio signal to transmit WiFi configuration data
+
+    config USE_ESP_BLUFI_WIFI_PROVISIONING
+        bool "Esp Blufi"
+        help
+            Use esp blufi protocol to transmit WiFi configuration data
+        select BT_ENABLED
+        select BT_BLE_42_FEATURES_SUPPORTED
+        select BT_BLE_BLUFI_ENABLE
+        select MBEDTLS_DHM_C
+endmenu
+
 config AUDIO_DEBUG_UDP_SERVER
     string "Audio Debug UDP Server Address"
     default "192.168.2.100:8000"
@@ -669,12 +752,6 @@ config AUDIO_DEBUG_UDP_SERVER
     help
         UDP server address, format: IP:PORT, used to receive audio debugging data
 
-config USE_ACOUSTIC_WIFI_PROVISIONING
-    bool "Enable Acoustic WiFi Provisioning"
-    default n
-    help
-        Enable acoustic WiFi provisioning, use audio signal to transmit WiFi configuration data
-
 config RECEIVE_CUSTOM_MESSAGE
     bool "Enable Custom Message Reception"
     default n
@@ -685,7 +762,7 @@ menu "Camera Configuration"
     depends on !IDF_TARGET_ESP32
 
     comment "Warning: Please read the help text before modifying these settings."
-    
+
     config XIAOZHI_CAMERA_ALLOW_JPEG_INPUT
         bool "Allow JPEG Input"
         default n

main/application.h

@@ -14,16 +14,23 @@
 #include "protocol.h"
 #include "ota.h"
 #include "audio_service.h"
-#include "device_state_event.h"
+#include "device_state.h"
+#include "device_state_machine.h"
 
-
-#define MAIN_EVENT_SCHEDULE (1 << 0)
-#define MAIN_EVENT_SEND_AUDIO (1 << 1)
-#define MAIN_EVENT_WAKE_WORD_DETECTED (1 << 2)
-#define MAIN_EVENT_VAD_CHANGE (1 << 3)
-#define MAIN_EVENT_ERROR (1 << 4)
-#define MAIN_EVENT_CHECK_NEW_VERSION_DONE (1 << 5)
-#define MAIN_EVENT_CLOCK_TICK (1 << 6)
+// Main event bits
+#define MAIN_EVENT_SCHEDULE             (1 << 0)
+#define MAIN_EVENT_SEND_AUDIO           (1 << 1)
+#define MAIN_EVENT_WAKE_WORD_DETECTED   (1 << 2)
+#define MAIN_EVENT_VAD_CHANGE           (1 << 3)
+#define MAIN_EVENT_ERROR                (1 << 4)
+#define MAIN_EVENT_ACTIVATION_DONE      (1 << 5)
+#define MAIN_EVENT_CLOCK_TICK           (1 << 6)
+#define MAIN_EVENT_NETWORK_CONNECTED    (1 << 7)
+#define MAIN_EVENT_NETWORK_DISCONNECTED (1 << 8)
+#define MAIN_EVENT_TOGGLE_CHAT          (1 << 9)
+#define MAIN_EVENT_START_LISTENING      (1 << 10)
+#define MAIN_EVENT_STOP_LISTENING       (1 << 11)
+#define MAIN_EVENT_STATE_CHANGED        (1 << 12)
 
 
 enum AecMode {
@@ -38,31 +45,80 @@ public:
         static Application instance;
         return instance;
     }
-    // 删除拷贝构造函数和赋值运算符
+    // Delete copy constructor and assignment operator
     Application(const Application&) = delete;
     Application& operator=(const Application&) = delete;
 
-    void Start();
-    void MainEventLoop();
-    DeviceState GetDeviceState() const { return device_state_; }
+    /**
+     * Initialize the application
+     * This sets up display, audio, network callbacks, etc.
+     * Network connection starts asynchronously.
+     */
+    void Initialize();
+
+    /**
+     * Run the main event loop
+     * This function runs in the main task and never returns.
+     * It handles all events including network, state changes, and user interactions.
+     */
+    void Run();
+
+    DeviceState GetDeviceState() const { return state_machine_.GetState(); }
     bool IsVoiceDetected() const { return audio_service_.IsVoiceDetected(); }
-    void Schedule(std::function<void()> callback);
-    void SetDeviceState(DeviceState state);
+    
+    /**
+     * Request state transition
+     * Returns true if transition was successful
+     */
+    bool SetDeviceState(DeviceState state);
+
+    /**
+     * Schedule a callback to be executed in the main task
+     */
+    void Schedule(std::function<void()>&& callback);
+
+    /**
+     * Alert with status, message, emotion and optional sound
+     */
     void Alert(const char* status, const char* message, const char* emotion = "", const std::string_view& sound = "");
     void DismissAlert();
+
     void AbortSpeaking(AbortReason reason);
+
+    /**
+     * Toggle chat state (event-based, thread-safe)
+     * Sends MAIN_EVENT_TOGGLE_CHAT to be handled in Run()
+     */
     void ToggleChatState();
+
+    /**
+     * Start listening (event-based, thread-safe)
+     * Sends MAIN_EVENT_START_LISTENING to be handled in Run()
+     */
     void StartListening();
+
+    /**
+     * Stop listening (event-based, thread-safe)
+     * Sends MAIN_EVENT_STOP_LISTENING to be handled in Run()
+     */
     void StopListening();
+
     void Reboot();
     void WakeWordInvoke(const std::string& wake_word);
-    bool UpgradeFirmware(Ota& ota, const std::string& url = "");
+    bool UpgradeFirmware(const std::string& url, const std::string& version = "");
     bool CanEnterSleepMode();
     void SendMcpMessage(const std::string& payload);
     void SetAecMode(AecMode mode);
     AecMode GetAecMode() const { return aec_mode_; }
     void PlaySound(const std::string_view& sound);
     AudioService& GetAudioService() { return audio_service_; }
+    
+    /**
+     * Reset protocol resources (thread-safe)
+     * Can be called from any task to release resources allocated after network connected
+     * This includes closing audio channel, resetting protocol and ota objects
+     */
+    void ResetProtocol();
 
 private:
     Application();
@@ -73,23 +129,46 @@ private:
     std::unique_ptr<Protocol> protocol_;
     EventGroupHandle_t event_group_ = nullptr;
     esp_timer_handle_t clock_timer_handle_ = nullptr;
-    volatile DeviceState device_state_ = kDeviceStateUnknown;
+    DeviceStateMachine state_machine_;
     ListeningMode listening_mode_ = kListeningModeAutoStop;
     AecMode aec_mode_ = kAecOff;
     std::string last_error_message_;
     AudioService audio_service_;
+    std::unique_ptr<Ota> ota_;
 
     bool has_server_time_ = false;
     bool aborted_ = false;
+    bool assets_version_checked_ = false;
+    bool play_popup_on_listening_ = false;  // Flag to play popup sound after state changes to listening
     int clock_ticks_ = 0;
-    TaskHandle_t check_new_version_task_handle_ = nullptr;
-    TaskHandle_t main_event_loop_task_handle_ = nullptr;
+    TaskHandle_t activation_task_handle_ = nullptr;
 
-    void OnWakeWordDetected();
-    void CheckNewVersion(Ota& ota);
+
+    // Event handlers
+    void HandleStateChangedEvent();
+    void HandleToggleChatEvent();
+    void HandleStartListeningEvent();
+    void HandleStopListeningEvent();
+    void HandleNetworkConnectedEvent();
+    void HandleNetworkDisconnectedEvent();
+    void HandleActivationDoneEvent();
+    void HandleWakeWordDetectedEvent();
+    void ContinueOpenAudioChannel(ListeningMode mode);
+    void ContinueWakeWordInvoke(const std::string& wake_word);
+
+    // Activation task (runs in background)
+    void ActivationTask();
+
+    // Helper methods
     void CheckAssetsVersion();
+    void CheckNewVersion();
+    void InitializeProtocol();
     void ShowActivationCode(const std::string& code, const std::string& message);
     void SetListeningMode(ListeningMode mode);
+    ListeningMode GetDefaultListeningMode() const;
+    
+    // State change handler called by state machine
+    void OnStateChanged(DeviceState old_state, DeviceState new_state);
 };
 
 

main/assets.cc

@@ -4,17 +4,20 @@
 #include "application.h"
 #include "lvgl_theme.h"
 #include "emote_display.h"
-#ifdef HAVE_LVGL
+#include "expression_emote.h"
+#if HAVE_LVGL
 #include "display/lcd_display.h"
+#include <spi_flash_mmap.h>
 #endif
 
 #include <esp_log.h>
-#include <spi_flash_mmap.h>
 #include <esp_timer.h>
+#include <esp_heap_caps.h>
 #include <cbin_font.h>
 
 
 #define TAG "Assets"
+#define PARTITION_LABEL "assets"
 
 struct mmap_assets_table {
     char asset_name[32];          /*!< Name of the asset */
@@ -24,19 +27,99 @@ struct mmap_assets_table {
     uint16_t asset_height;        /*!< Height of the asset */
 };
 
-
 Assets::Assets() {
+#if HAVE_LVGL
+    strategy_ = std::make_unique<Assets::LvglStrategy>();
+#else
+    strategy_ = std::make_unique<Assets::EmoteStrategy>();
+#endif
     // Initialize the partition
     InitializePartition();
 }
 
 Assets::~Assets() {
-    if (mmap_handle_ != 0) {
-        esp_partition_munmap(mmap_handle_);
+    UnApplyPartition();
+}
+
+bool Assets::FindPartition(Assets* assets) {
+    assets->partition_ = esp_partition_find_first(ESP_PARTITION_TYPE_ANY, ESP_PARTITION_SUBTYPE_ANY, PARTITION_LABEL);
+    if (assets->partition_ == nullptr) {
+        ESP_LOGI(TAG, "No assets partition found");
+        return false;
+    }
+    return true;
+}
+
+bool Assets::Apply() {
+    return strategy_ ? strategy_->Apply(this) : false;
+}
+
+bool Assets::InitializePartition() {
+    return strategy_ ? strategy_->InitializePartition(this) : false;
+}
+
+void Assets::UnApplyPartition() {
+    if (strategy_) {
+        strategy_->UnApplyPartition(this);
     }
 }
 
-uint32_t Assets::CalculateChecksum(const char* data, uint32_t length) {
+bool Assets::GetAssetData(const std::string& name, void*& ptr, size_t& size) {
+    return strategy_ ? strategy_->GetAssetData(this, name, ptr, size) : false;
+}
+
+bool Assets::LoadSrmodelsFromIndex(Assets* assets, cJSON* root) {
+    void* ptr = nullptr;
+    size_t size = 0;
+    bool need_delete_root = false;
+
+    // If root is not provided, parse index.json
+    if (root == nullptr) {
+        if (!assets->GetAssetData("index.json", ptr, size)) {
+            ESP_LOGE(TAG, "The index.json file is not found");
+            return false;
+        }
+
+        root = cJSON_ParseWithLength(static_cast<char*>(ptr), size);
+        if (root == nullptr) {
+            ESP_LOGE(TAG, "The index.json file is not valid");
+            return false;
+        }
+        need_delete_root = true;
+    }
+
+    cJSON* srmodels = cJSON_GetObjectItem(root, "srmodels");
+    if (cJSON_IsString(srmodels)) {
+        std::string srmodels_file = srmodels->valuestring;
+        if (assets->GetAssetData(srmodels_file, ptr, size)) {
+            if (assets->models_list_ != nullptr) {
+                esp_srmodel_deinit(assets->models_list_);
+                assets->models_list_ = nullptr;
+            }
+            assets->models_list_ = srmodel_load(static_cast<uint8_t*>(ptr));
+            if (assets->models_list_ != nullptr) {
+                auto& app = Application::GetInstance();
+                app.GetAudioService().SetModelsList(assets->models_list_);
+                if (need_delete_root) {
+                    cJSON_Delete(root);
+                }
+                return true;
+            } else {
+                ESP_LOGE(TAG, "Failed to load srmodels.bin");
+            }
+        } else {
+            ESP_LOGE(TAG, "The srmodels file %s is not found", srmodels_file.c_str());
+        }
+    }
+
+    if (need_delete_root) {
+        cJSON_Delete(root);
+    }
+    return false;
+}
+
+#if HAVE_LVGL
+uint32_t Assets::LvglStrategy::CalculateChecksum(const char* data, uint32_t length) {
     uint32_t checksum = 0;
     for (uint32_t i = 0; i < length; i++) {
         checksum += data[i];
@@ -44,40 +127,37 @@ uint32_t Assets::CalculateChecksum(const char* data, uint32_t length) {
     return checksum & 0xFFFF;
 }
 
-bool Assets::InitializePartition() {
-    partition_valid_ = false;
-    checksum_valid_ = false;
+bool Assets::LvglStrategy::InitializePartition(Assets* assets) {
+    assets->partition_valid_ = false;
     assets_.clear();
 
-    partition_ = esp_partition_find_first(ESP_PARTITION_TYPE_ANY, ESP_PARTITION_SUBTYPE_ANY, "assets");
-    if (partition_ == nullptr) {
-        ESP_LOGI(TAG, "No assets partition found");
+    if (!Assets::FindPartition(assets)) {
         return false;
     }
 
     int free_pages = spi_flash_mmap_get_free_pages(SPI_FLASH_MMAP_DATA);
     uint32_t storage_size = free_pages * 64 * 1024;
     ESP_LOGI(TAG, "The storage free size is %ld KB", storage_size / 1024);
-    ESP_LOGI(TAG, "The partition size is %ld KB", partition_->size / 1024);
-    if (storage_size < partition_->size) {
-        ESP_LOGE(TAG, "The free size %ld KB is less than assets partition required %ld KB", storage_size / 1024, partition_->size / 1024);
+    ESP_LOGI(TAG, "The partition size is %ld KB", assets->partition_->size / 1024);
+    if (storage_size < assets->partition_->size) {
+        ESP_LOGE(TAG, "The free size %ld KB is less than assets partition required %ld KB", storage_size / 1024, assets->partition_->size / 1024);
         return false;
     }
 
-    esp_err_t err = esp_partition_mmap(partition_, 0, partition_->size, ESP_PARTITION_MMAP_DATA, (const void**)&mmap_root_, &mmap_handle_);
+    esp_err_t err = esp_partition_mmap(assets->partition_, 0, assets->partition_->size, ESP_PARTITION_MMAP_DATA, (const void**)&mmap_root_, &mmap_handle_);
     if (err != ESP_OK) {
         ESP_LOGE(TAG, "Failed to mmap assets partition: %s", esp_err_to_name(err));
         return false;
     }
 
-    partition_valid_ = true;
+    assets->partition_valid_ = true;
 
     uint32_t stored_files = *(uint32_t*)(mmap_root_ + 0);
     uint32_t stored_chksum = *(uint32_t*)(mmap_root_ + 4);
     uint32_t stored_len = *(uint32_t*)(mmap_root_ + 8);
 
-    if (stored_len > partition_->size - 12) {
-        ESP_LOGD(TAG, "The stored_len (0x%lx) is greater than the partition size (0x%lx) - 12", stored_len, partition_->size);
+    if (stored_len > assets->partition_->size - 12) {
+        ESP_LOGD(TAG, "The stored_len (0x%lx) is greater than the partition size (0x%lx) - 12", stored_len, assets->partition_->size);
         return false;
     }
 
@@ -104,10 +184,37 @@ bool Assets::InitializePartition() {
     return checksum_valid_;
 }
 
-bool Assets::Apply() {
+void Assets::LvglStrategy::UnApplyPartition(Assets* assets) {
+    if (mmap_handle_ != 0) {
+        esp_partition_munmap(mmap_handle_);
+        mmap_handle_ = 0;
+        mmap_root_ = nullptr;
+    }
+    checksum_valid_ = false;
+    assets_.clear();
+    (void)assets; // Unused parameter
+}
+
+bool Assets::LvglStrategy::GetAssetData(Assets* assets, const std::string& name, void*& ptr, size_t& size) {
+    auto asset = assets_.find(name);
+    if (asset == assets_.end()) {
+        return false;
+    }
+    auto data = (const char*)(mmap_root_ + asset->second.offset);
+    if (data[0] != 'Z' || data[1] != 'Z') {
+        ESP_LOGE(TAG, "The asset %s is not valid with magic %02x%02x", name.c_str(), data[0], data[1]);
+        return false;
+    }
+
+    ptr = static_cast<void*>(const_cast<char*>(data + 2));
+    size = asset->second.size;
+    return true;
+}
+
+bool Assets::LvglStrategy::Apply(Assets* assets) {
     void* ptr = nullptr;
     size_t size = 0;
-    if (!GetAssetData("index.json", ptr, size)) {
+    if (!assets->GetAssetData("index.json", ptr, size)) {
         ESP_LOGE(TAG, "The index.json file is not found");
         return false;
     }
@@ -125,28 +232,9 @@ bool Assets::Apply() {
             return false;
         }
     }
-    
-    cJSON* srmodels = cJSON_GetObjectItem(root, "srmodels");
-    if (cJSON_IsString(srmodels)) {
-        std::string srmodels_file = srmodels->valuestring;
-        if (GetAssetData(srmodels_file, ptr, size)) {
-            if (models_list_ != nullptr) {
-                esp_srmodel_deinit(models_list_);
-                models_list_ = nullptr;
-            }
-            models_list_ = srmodel_load(static_cast<uint8_t*>(ptr));
-            if (models_list_ != nullptr) {
-                auto& app = Application::GetInstance();
-                app.GetAudioService().SetModelsList(models_list_);
-            } else {
-                ESP_LOGE(TAG, "Failed to load srmodels.bin");
-            }
-        } else {
-            ESP_LOGE(TAG, "The srmodels file %s is not found", srmodels_file.c_str());
-        }
-    }
 
-#ifdef HAVE_LVGL
+    Assets::LoadSrmodelsFromIndex(assets, root);
+
     auto& theme_manager = LvglThemeManager::GetInstance();
     auto light_theme = theme_manager.GetTheme("light");
     auto dark_theme = theme_manager.GetTheme("dark");
@@ -154,7 +242,7 @@ bool Assets::Apply() {
     cJSON* font = cJSON_GetObjectItem(root, "text_font");
     if (cJSON_IsString(font)) {
         std::string fonts_text_file = font->valuestring;
-        if (GetAssetData(fonts_text_file, ptr, size)) {
+        if (assets->GetAssetData(fonts_text_file, ptr, size)) {
             auto text_font = std::make_shared<LvglCBinFont>(ptr);
             if (text_font->font() == nullptr) {
                 ESP_LOGE(TAG, "Failed to load fonts.bin");
@@ -182,7 +270,7 @@ bool Assets::Apply() {
                 cJSON* file = cJSON_GetObjectItem(emoji, "file");
                 cJSON* eaf = cJSON_GetObjectItem(emoji, "eaf");
                 if (cJSON_IsString(name) && cJSON_IsString(file) && (NULL== eaf)) {
-                    if (!GetAssetData(file->valuestring, ptr, size)) {
+                    if (!assets->GetAssetData(file->valuestring, ptr, size)) {
                         ESP_LOGE(TAG, "Emoji %s image file %s is not found", name->valuestring, file->valuestring);
                         continue;
                     }
@@ -213,7 +301,7 @@ bool Assets::Apply() {
                 light_theme->set_chat_background_color(LvglTheme::ParseColor(background_color->valuestring));
             }
             if (cJSON_IsString(background_image)) {
-                if (!GetAssetData(background_image->valuestring, ptr, size)) {
+                if (!assets->GetAssetData(background_image->valuestring, ptr, size)) {
                     ESP_LOGE(TAG, "The background image file %s is not found", background_image->valuestring);
                     return false;
                 }
@@ -234,7 +322,7 @@ bool Assets::Apply() {
                 dark_theme->set_chat_background_color(LvglTheme::ParseColor(background_color->valuestring));
             }
             if (cJSON_IsString(background_image)) {
-                if (!GetAssetData(background_image->valuestring, ptr, size)) {
+                if (!assets->GetAssetData(background_image->valuestring, ptr, size)) {
                     ESP_LOGE(TAG, "The background image file %s is not found", background_image->valuestring);
                     return false;
                 }
@@ -262,137 +350,84 @@ bool Assets::Apply() {
             ESP_LOGI(TAG, "Set hide_subtitle to %s", hide ? "true" : "false");
         }
     }
-
-#elif defined(CONFIG_USE_EMOTE_MESSAGE_STYLE)
-    auto &board = Board::GetInstance();
-    auto display = board.GetDisplay();
-    auto emote_display = dynamic_cast<emote::EmoteDisplay*>(display);
-
-    cJSON* font = cJSON_GetObjectItem(root, "text_font");
-    if (cJSON_IsString(font)) {
-        std::string fonts_text_file = font->valuestring;
-        if (GetAssetData(fonts_text_file, ptr, size)) {
-            auto text_font = std::make_shared<LvglCBinFont>(ptr);
-            if (text_font->font() == nullptr) {
-                ESP_LOGE(TAG, "Failed to load fonts.bin");
-                return false;
-            }
-
-            if (emote_display) {
-                emote_display->AddTextFont(text_font);
-            }
-        } else {
-            ESP_LOGE(TAG, "The font file %s is not found", fonts_text_file.c_str());
-        }
-    }
-
-    cJSON* emoji_collection = cJSON_GetObjectItem(root, "emoji_collection");
-    if (cJSON_IsArray(emoji_collection)) {
-        int emoji_count = cJSON_GetArraySize(emoji_collection);
-        if (emote_display) {
-            for (int i = 0; i < emoji_count; i++) {
-                cJSON* icon = cJSON_GetArrayItem(emoji_collection, i);
-                if (cJSON_IsObject(icon)) {
-                    cJSON* name = cJSON_GetObjectItem(icon, "name");
-                    cJSON* file = cJSON_GetObjectItem(icon, "file");
-
-                    if (cJSON_IsString(name) && cJSON_IsString(file)) {
-                        if (GetAssetData(file->valuestring, ptr, size)) {
-                            cJSON* eaf = cJSON_GetObjectItem(icon, "eaf");
-                            bool lack_value = false;
-                            bool loop_value = false;
-                            int fps_value = 0;
-
-                            if (cJSON_IsObject(eaf)) {
-                                cJSON* lack = cJSON_GetObjectItem(eaf, "lack");
-                                cJSON* loop = cJSON_GetObjectItem(eaf, "loop");
-                                cJSON* fps = cJSON_GetObjectItem(eaf, "fps");
-
-                                lack_value = lack ? cJSON_IsTrue(lack) : false;
-                                loop_value = loop ? cJSON_IsTrue(loop) : false;
-                                fps_value = fps ? fps->valueint : 0;
-
-                                emote_display->AddEmojiData(name->valuestring, ptr, size,
-                                                          static_cast<uint8_t>(fps_value),
-                                                          loop_value, lack_value);
-                            }
-
-                        } else {
-                            ESP_LOGE(TAG, "Emoji \"%10s\" image file %s is not found", name->valuestring, file->valuestring);
-                        }
-                    }
-                }
-            }
-        }
-    }
-
-    cJSON* icon_collection = cJSON_GetObjectItem(root, "icon_collection");
-    if (cJSON_IsArray(icon_collection)) {
-        if (emote_display) {
-            int icon_count = cJSON_GetArraySize(icon_collection);
-            for (int i = 0; i < icon_count; i++) {
-                cJSON* icon = cJSON_GetArrayItem(icon_collection, i);
-                if (cJSON_IsObject(icon)) {
-                    cJSON* name = cJSON_GetObjectItem(icon, "name");
-                    cJSON* file = cJSON_GetObjectItem(icon, "file");
-
-                    if (cJSON_IsString(name) && cJSON_IsString(file)) {
-                        if (GetAssetData(file->valuestring, ptr, size)) {
-                            emote_display->AddIconData(name->valuestring, ptr, size);
-                        } else {
-                            ESP_LOGE(TAG, "Icon \"%10s\" image file %s is not found", name->valuestring, file->valuestring);
-                        }
-                    }
-                }
-            }
-        }
-    }
-
-    cJSON* layout_json = cJSON_GetObjectItem(root, "layout");
-    if (cJSON_IsArray(layout_json)) {
-        int layout_count = cJSON_GetArraySize(layout_json);
-
-        for (int i = 0; i < layout_count; i++) {
-            cJSON* layout_item = cJSON_GetArrayItem(layout_json, i);
-            if (cJSON_IsObject(layout_item)) {
-                cJSON* name = cJSON_GetObjectItem(layout_item, "name");
-                cJSON* align = cJSON_GetObjectItem(layout_item, "align");
-                cJSON* x = cJSON_GetObjectItem(layout_item, "x");
-                cJSON* y = cJSON_GetObjectItem(layout_item, "y");
-                cJSON* width = cJSON_GetObjectItem(layout_item, "width");
-                cJSON* height = cJSON_GetObjectItem(layout_item, "height");
-
-                if (cJSON_IsString(name) && cJSON_IsString(align) && cJSON_IsNumber(x) && cJSON_IsNumber(y)) {
-                    int width_val = cJSON_IsNumber(width) ? width->valueint : 0;
-                    int height_val = cJSON_IsNumber(height) ? height->valueint : 0;
-
-                    if (emote_display) {
-                        emote_display->AddLayoutData(name->valuestring, align->valuestring,
-                                                     x->valueint, y->valueint, width_val, height_val);
-                    }
-                } else {
-                    ESP_LOGW(TAG, "Invalid layout item %d: missing required fields", i);
-                }
-            }
-        }
-    }
-#endif
-
+    
     cJSON_Delete(root);
     return true;
 }
+#endif // HAVE_LVGL
+
+bool Assets::EmoteStrategy::InitializePartition(Assets* assets) {
+    assets->partition_valid_ = false;
+
+    if (!Assets::FindPartition(assets)) {
+        return false;
+    }
+
+    esp_err_t ret = ESP_ERR_INVALID_STATE;
+    auto display = Board::GetInstance().GetDisplay();
+    auto* emote_display = dynamic_cast<emote::EmoteDisplay*>(display);
+    if (emote_display && emote_display->GetEmoteHandle() != nullptr) {
+        const emote_data_t data = {
+            .type = EMOTE_SOURCE_PARTITION,
+            .source = {
+                .partition_label = PARTITION_LABEL,
+            },
+            .flags = {
+                .mmap_enable = true, //must be true here!!!
+            },
+        };
+        ret = emote_mount_assets(emote_display->GetEmoteHandle(), &data);
+    } else {
+        ESP_LOGE(TAG, "Emote display is not initialized");
+    }
+    assets->partition_valid_ = ((ret == ESP_OK) ? true : false);
+    return assets->partition_valid_;
+}
+
+void Assets::EmoteStrategy::UnApplyPartition(Assets* assets) {
+    auto display = Board::GetInstance().GetDisplay();
+    auto* emote_display = dynamic_cast<emote::EmoteDisplay*>(display);
+    if (emote_display && emote_display->GetEmoteHandle() != nullptr) {
+        emote_unmount_assets(emote_display->GetEmoteHandle());
+    }
+    (void)assets; // Unused parameter
+}
+
+bool Assets::EmoteStrategy::GetAssetData(Assets* assets, const std::string& name, void*& ptr, size_t& size) {
+    auto display = Board::GetInstance().GetDisplay();
+    auto* emote_display = dynamic_cast<emote::EmoteDisplay*>(display);
+    if (emote_display && emote_display->GetEmoteHandle() != nullptr) {
+        const uint8_t* data = nullptr;
+        size_t data_size = 0;
+        if (ESP_OK == emote_get_asset_data_by_name(emote_display->GetEmoteHandle(), name.c_str(), &data, &data_size)) {
+            ptr = const_cast<void*>(static_cast<const void*>(data));
+            size = data_size;
+            return true;
+        }
+        ESP_LOGE(TAG, "Failed to get asset data by name: %s", name.c_str());
+        return false;
+    }
+    (void)assets; // Unused parameter
+    return false;
+}
+
+bool Assets::EmoteStrategy::Apply(Assets* assets) {
+    Assets::LoadSrmodelsFromIndex(assets);
+
+    auto display = Board::GetInstance().GetDisplay();
+    auto* emote_display = dynamic_cast<emote::EmoteDisplay*>(display);
+
+    if (emote_display && emote_display->GetEmoteHandle() != nullptr) {
+        emote_load_assets(emote_display->GetEmoteHandle());
+    }
+    return true;
+}
 
 bool Assets::Download(std::string url, std::function<void(int progress, size_t speed)> progress_callback) {
     ESP_LOGI(TAG, "Downloading new version of assets from %s", url.c_str());
-    
+
     // 取消当前资源分区的内存映射
-    if (mmap_handle_ != 0) {
-        esp_partition_munmap(mmap_handle_);
-        mmap_handle_ = 0;
-        mmap_root_ = nullptr;
-    }
-    checksum_valid_ = false;
-    assets_.clear();
+    UnApplyPartition();
 
     // 下载新的资源文件
     auto network = Board::GetInstance().GetNetwork();
@@ -430,16 +465,21 @@ bool Assets::Download(std::string url, std::function<void(int progress, size_t s
              SECTOR_SIZE, content_length, sectors_to_erase, total_erase_size);
     
     // 写入新的资源文件到分区，一边erase一边写入
-    char buffer[512];
+    char* buffer = (char*)heap_caps_malloc(SECTOR_SIZE, MALLOC_CAP_INTERNAL);
+    if (buffer == nullptr) {
+        ESP_LOGE(TAG, "Failed to allocate buffer");
+        return false;
+    }
     size_t total_written = 0;
     size_t recent_written = 0;
     size_t current_sector = 0;
     auto last_calc_time = esp_timer_get_time();
     
     while (true) {
-        int ret = http->Read(buffer, sizeof(buffer));
+        int ret = http->Read(buffer, SECTOR_SIZE);
         if (ret < 0) {
             ESP_LOGE(TAG, "Failed to read HTTP data: %s", esp_err_to_name(ret));
+            heap_caps_free(buffer);
             return false;
         }
 
@@ -459,6 +499,7 @@ bool Assets::Download(std::string url, std::function<void(int progress, size_t s
             // 确保擦除范围不超过分区大小
             if (sector_end > partition_->size) {
                 ESP_LOGE(TAG, "Sector end (%u) exceeds partition size (%lu)", sector_end, partition_->size);
+                heap_caps_free(buffer);
                 return false;
             }
             
@@ -466,6 +507,7 @@ bool Assets::Download(std::string url, std::function<void(int progress, size_t s
             esp_err_t err = esp_partition_erase_range(partition_, sector_start, SECTOR_SIZE);
             if (err != ESP_OK) {
                 ESP_LOGE(TAG, "Failed to erase sector %u at offset %u: %s", current_sector, sector_start, esp_err_to_name(err));
+                heap_caps_free(buffer);
                 return false;
             }
             
@@ -476,6 +518,7 @@ bool Assets::Download(std::string url, std::function<void(int progress, size_t s
         esp_err_t err = esp_partition_write(partition_, total_written, buffer, ret);
         if (err != ESP_OK) {
             ESP_LOGE(TAG, "Failed to write to assets partition at offset %u: %s", total_written, esp_err_to_name(err));
+            heap_caps_free(buffer);
             return false;
         }
 
@@ -497,6 +540,7 @@ bool Assets::Download(std::string url, std::function<void(int progress, size_t s
     }
     
     http->Close();
+    heap_caps_free(buffer);
 
     if (total_written != content_length) {
         ESP_LOGE(TAG, "Downloaded size (%u) does not match expected size (%u)", total_written, content_length);
@@ -514,19 +558,3 @@ bool Assets::Download(std::string url, std::function<void(int progress, size_t s
 
     return true;
 }
-
-bool Assets::GetAssetData(const std::string& name, void*& ptr, size_t& size) {
-    auto asset = assets_.find(name);
-    if (asset == assets_.end()) {
-        return false;
-    }
-    auto data = (const char*)(mmap_root_ + asset->second.offset);
-    if (data[0] != 'Z' || data[1] != 'Z') {
-        ESP_LOGE(TAG, "The asset %s is not valid with magic %02x%02x", name.c_str(), data[0], data[1]);
-        return false;
-    }
-
-    ptr = static_cast<void*>(const_cast<char*>(data + 2));
-    size = asset->second.size;
-    return true;
-}

main/assets.h

@@ -1,14 +1,19 @@
 #ifndef ASSETS_H
 #define ASSETS_H
 
-#include <map>
 #include <string>
 #include <functional>
+#include <memory>
 
 #include <cJSON.h>
 #include <esp_partition.h>
 #include <model_path.h>
+#include <map>
+#include <string>
 
+#if HAVE_LVGL
+#include <spi_flash_mmap.h>
+#endif
 
 struct Asset {
     size_t size;
@@ -28,7 +33,6 @@ public:
     bool GetAssetData(const std::string& name, void*& ptr, size_t& size);
 
     inline bool partition_valid() const { return partition_valid_; }
-    inline bool checksum_valid() const { return checksum_valid_; }
     inline std::string default_assets_url() const { return default_assets_url_; }
 
 private:
@@ -37,16 +41,49 @@ private:
     Assets& operator=(const Assets&) = delete;
 
     bool InitializePartition();
-    uint32_t CalculateChecksum(const char* data, uint32_t length);
+    void UnApplyPartition();
+    static bool FindPartition(Assets* assets);
+    static bool LoadSrmodelsFromIndex(Assets* assets, cJSON* root = nullptr);
+  
+    class AssetStrategy {
+    public:
+        virtual ~AssetStrategy() = default;
+        virtual bool Apply(Assets* assets) = 0;
+        virtual bool InitializePartition(Assets* assets) = 0;
+        virtual void UnApplyPartition(Assets* assets) = 0;
+        virtual bool GetAssetData(Assets* assets, const std::string& name, void*& ptr, size_t& size) = 0;
+    };
+    
+    class LvglStrategy : public AssetStrategy {
+    public:
+        bool Apply(Assets* assets) override;
+        bool InitializePartition(Assets* assets) override;
+        void UnApplyPartition(Assets* assets) override;
+        bool GetAssetData(Assets* assets, const std::string& name, void*& ptr, size_t& size) override;
+    private:
+        static uint32_t CalculateChecksum(const char* data, uint32_t length);
+        std::map<std::string, Asset> assets_;
+        esp_partition_mmap_handle_t mmap_handle_ = 0;
+        const char* mmap_root_ = nullptr;
+        bool checksum_valid_ = false;
+    };
+    
+    class EmoteStrategy : public AssetStrategy {
+    public:
+        bool Apply(Assets* assets) override;
+        bool InitializePartition(Assets* assets) override;
+        void UnApplyPartition(Assets* assets) override;
+        bool GetAssetData(Assets* assets, const std::string& name, void*& ptr, size_t& size) override;
+    };
+    
+    // Strategy instance
+    std::unique_ptr<AssetStrategy> strategy_;
 
+protected:
     const esp_partition_t* partition_ = nullptr;
-    esp_partition_mmap_handle_t mmap_handle_ = 0;
-    const char* mmap_root_ = nullptr;
     bool partition_valid_ = false;
-    bool checksum_valid_ = false;
     std::string default_assets_url_;
     srmodel_list_t* models_list_ = nullptr;
-    std::map<std::string, Asset> assets_;
 };
 
 #endif

main/assets/locales/ar-SA/language.json

@@ -50,6 +50,10 @@
         "LOADING_ASSETS": "جاري تحميل الموارد...",
         "PLEASE_WAIT": "يرجى الانتظار...",
         "FOUND_NEW_ASSETS": "تم العثور على موارد جديدة: %s",
-        "HELLO_MY_FRIEND": "مرحباً، صديقي!"
+        "HELLO_MY_FRIEND": "مرحباً، صديقي!",
+        "CONNECTION_SUCCESSFUL": "تم الاتصال بنجاح",
+        "FLIGHT_MODE_OFF": "وضع الطيران معطل",
+        "FLIGHT_MODE_ON": "وضع الطيران قيد التشغيل",
+        "MODEM_INIT_ERROR": "فشل تهيئة المودم"
     }
 }

main/assets/locales/bg-BG/language.json

@@ -51,7 +51,9 @@
         "FOUND_NEW_ASSETS": "Намерени нови ресурси: %s",
         "DOWNLOAD_ASSETS_FAILED": "Неуспешно изтегляне на ресурси",
         "LOADING_ASSETS": "Зареждане на ресурси...",
-        "HELLO_MY_FRIEND": "Здравей, мой приятел!"
+        "HELLO_MY_FRIEND": "Здравей, мой приятел!",
+        "FLIGHT_MODE_OFF": "Режим на самолет е изключен",
+        "FLIGHT_MODE_ON": "Режим на самолет е включен",
+        "MODEM_INIT_ERROR": "Неуспешна инициализация на модема"
     }
-}
-
+}

main/assets/locales/ca-ES/language.json

@@ -51,7 +51,9 @@
         "FOUND_NEW_ASSETS": "S'han trobat nous recursos: %s",
         "DOWNLOAD_ASSETS_FAILED": "No s'han pogut descarregar els recursos",
         "LOADING_ASSETS": "Carregant recursos...",
-        "HELLO_MY_FRIEND": "Hola, amic meu!"
+        "HELLO_MY_FRIEND": "Hola, amic meu!",
+        "FLIGHT_MODE_OFF": "El mode avió està desactivat",
+        "FLIGHT_MODE_ON": "El mode avió està activat",
+        "MODEM_INIT_ERROR": "Error d'inicialització del mòdem"
     }
-}
-
+}

main/assets/locales/cs-CZ/language.json

@@ -50,6 +50,10 @@
         "LOADING_ASSETS": "Načítání prostředků...",
         "PLEASE_WAIT": "Prosím čekejte...",
         "FOUND_NEW_ASSETS": "Nalezeny nové prostředky: %s",
-        "HELLO_MY_FRIEND": "Ahoj, můj příteli!"
+        "HELLO_MY_FRIEND": "Ahoj, můj příteli!",
+        "CONNECTION_SUCCESSFUL": "Připojení úspěšné",
+        "FLIGHT_MODE_OFF": "Letecký režim je vypnutý",
+        "FLIGHT_MODE_ON": "Letecký režim je zapnutý",
+        "MODEM_INIT_ERROR": "Chyba inicializace modemu"
     }
 }

main/assets/locales/da-DK/language.json

@@ -51,7 +51,9 @@
         "FOUND_NEW_ASSETS": "Fandt nye ressourcer: %s",
         "DOWNLOAD_ASSETS_FAILED": "Download af ressourcer mislykkedes",
         "LOADING_ASSETS": "Indlæser ressourcer...",
-        "HELLO_MY_FRIEND": "Hej, min ven!"
+        "HELLO_MY_FRIEND": "Hej, min ven!",
+        "FLIGHT_MODE_OFF": "Flytilstand er slukket",
+        "FLIGHT_MODE_ON": "Flytilstand er tændt",
+        "MODEM_INIT_ERROR": "Modeminitialisering mislykkedes"
     }
-}
-
+}

main/assets/locales/de-DE/language.json

@@ -50,6 +50,10 @@
         "LOADING_ASSETS": "Ressourcen werden geladen...",
         "PLEASE_WAIT": "Bitte warten...",
         "FOUND_NEW_ASSETS": "Neue Ressourcen gefunden: %s",
-        "HELLO_MY_FRIEND": "Hallo, mein Freund!"
+        "HELLO_MY_FRIEND": "Hallo, mein Freund!",
+        "CONNECTION_SUCCESSFUL": "Verbindung erfolgreich",
+        "FLIGHT_MODE_OFF": "Flugmodus ist deaktiviert",
+        "FLIGHT_MODE_ON": "Flugmodus ist aktiviert",
+        "MODEM_INIT_ERROR": "Modem-Initialisierung fehlgeschlagen"
     }
 }

main/assets/locales/el-GR/language.json

@@ -51,7 +51,9 @@
         "FOUND_NEW_ASSETS": "Βρέθηκαν νέοι πόροι: %s",
         "DOWNLOAD_ASSETS_FAILED": "Αποτυχία λήψης πόρων",
         "LOADING_ASSETS": "Φόρτωση πόρων...",
-        "HELLO_MY_FRIEND": "Γεια σου, φίλε μου!"
+        "HELLO_MY_FRIEND": "Γεια σου, φίλε μου!",
+        "FLIGHT_MODE_OFF": "Η λειτουργία πτήσης είναι απενεργοποιημένη",
+        "FLIGHT_MODE_ON": "Η λειτουργία πτήσης είναι ενεργή",
+        "MODEM_INIT_ERROR": "Αποτυχία αρχικοποίησης modem"
     }
-}
-
+}

main/assets/locales/en-US/language.json

@@ -11,7 +11,10 @@
         "INITIALIZING": "Initializing...",
         "PIN_ERROR": "Please insert SIM card",
         "REG_ERROR": "Unable to access network, please check SIM card status",
+        "MODEM_INIT_ERROR": "Modem initialization failed",
         "DETECTING_MODULE": "Detecting module...",
+        "FLIGHT_MODE_ON": "Flight mode is on",
+        "FLIGHT_MODE_OFF": "Flight mode is off",
         "REGISTERING_NETWORK": "Waiting for network...",
         "CHECKING_NEW_VERSION": "Checking for new version...",
         "CHECK_NEW_VERSION_FAILED": "Check for new version failed, will retry in %d seconds: %s",

main/assets/locales/es-ES/language.json

@@ -50,6 +50,10 @@
         "LOADING_ASSETS": "Cargando recursos...",
         "PLEASE_WAIT": "Por favor espere...",
         "FOUND_NEW_ASSETS": "Encontrados nuevos recursos: %s",
-        "HELLO_MY_FRIEND": "¡Hola, mi amigo!"
+        "HELLO_MY_FRIEND": "¡Hola, mi amigo!",
+        "CONNECTION_SUCCESSFUL": "Conexión exitosa",
+        "FLIGHT_MODE_OFF": "El modo avión está desactivado",
+        "FLIGHT_MODE_ON": "El modo avión está activado",
+        "MODEM_INIT_ERROR": "Error de inicialización del módem"
     }
 }

main/assets/locales/fa-IR/language.json

@@ -51,7 +51,9 @@
         "FOUND_NEW_ASSETS": "منابع جدید یافت شد: %s",
         "DOWNLOAD_ASSETS_FAILED": "دانلود منابع ناموفق بود",
         "LOADING_ASSETS": "بارگذاری منابع...",
-        "HELLO_MY_FRIEND": "سلام، دوست من!"
+        "HELLO_MY_FRIEND": "سلام، دوست من!",
+        "FLIGHT_MODE_OFF": "حالت پرواز خاموش است",
+        "FLIGHT_MODE_ON": "حالت پرواز روشن است",
+        "MODEM_INIT_ERROR": "خطا در راه‌اندازی مودم"
     }
-}
-
+}

main/assets/locales/fi-FI/language.json

@@ -50,6 +50,10 @@
         "LOADING_ASSETS": "Ladataan resursseja...",
         "PLEASE_WAIT": "Odota hetki...",
         "FOUND_NEW_ASSETS": "Löydetty uusia resursseja: %s",
-        "HELLO_MY_FRIEND": "Hei, ystäväni!"
+        "HELLO_MY_FRIEND": "Hei, ystäväni!",
+        "CONNECTION_SUCCESSFUL": "Yhteys onnistui",
+        "FLIGHT_MODE_OFF": "Lentotila on pois päältä",
+        "FLIGHT_MODE_ON": "Lentotila on päällä",
+        "MODEM_INIT_ERROR": "Modeemin alustus epäonnistui"
     }
 }

main/assets/locales/fil-PH/language.json

@@ -51,7 +51,9 @@
         "FOUND_NEW_ASSETS": "Nakahanap ng mga bagong assets: %s",
         "DOWNLOAD_ASSETS_FAILED": "Nabigo ang pag-download ng mga assets",
         "LOADING_ASSETS": "Nilo-load ang mga assets...",
-        "HELLO_MY_FRIEND": "Kumusta, kaibigan ko!"
+        "HELLO_MY_FRIEND": "Kumusta, kaibigan ko!",
+        "FLIGHT_MODE_OFF": "Naka-off ang flight mode",
+        "FLIGHT_MODE_ON": "Naka-on ang flight mode",
+        "MODEM_INIT_ERROR": "Nabigo ang pag-initialize ng modem"
     }
-}
-
+}

main/assets/locales/fr-FR/language.json

@@ -50,6 +50,10 @@
         "LOADING_ASSETS": "Chargement des ressources...",
         "PLEASE_WAIT": "Veuillez patienter...",
         "FOUND_NEW_ASSETS": "Nouvelles ressources trouvées: %s",
-        "HELLO_MY_FRIEND": "Bonjour, mon ami !"
+        "HELLO_MY_FRIEND": "Bonjour, mon ami !",
+        "CONNECTION_SUCCESSFUL": "Connexion réussie",
+        "FLIGHT_MODE_OFF": "Le mode avion est désactivé",
+        "FLIGHT_MODE_ON": "Le mode avion est activé",
+        "MODEM_INIT_ERROR": "Échec de l'initialisation du modem"
     }
 }

main/assets/locales/he-IL/language.json

@@ -51,7 +51,9 @@
         "FOUND_NEW_ASSETS": "נמצאו משאבים חדשים: %s",
         "DOWNLOAD_ASSETS_FAILED": "הורדת משאבים נכשלה",
         "LOADING_ASSETS": "טוען משאבים...",
-        "HELLO_MY_FRIEND": "שלום, ידידי!"
+        "HELLO_MY_FRIEND": "שלום, ידידי!",
+        "FLIGHT_MODE_OFF": "מצב טיסה כבוי",
+        "FLIGHT_MODE_ON": "מצב טיסה מופעל",
+        "MODEM_INIT_ERROR": "אתחול המודם נכשל"
     }
-}
-
+}

main/assets/locales/hi-IN/language.json

@@ -50,6 +50,10 @@
         "LOADING_ASSETS": "संसाधन लोड हो रहे हैं...",
         "PLEASE_WAIT": "कृपया प्रतीक्षा करें...",
         "FOUND_NEW_ASSETS": "नए संसाधन मिले: %s",
-        "HELLO_MY_FRIEND": "नमस्ते, मेरे दोस्त!"
+        "HELLO_MY_FRIEND": "नमस्ते, मेरे दोस्त!",
+        "CONNECTION_SUCCESSFUL": "कनेक्शन सफल",
+        "FLIGHT_MODE_OFF": "फ़्लाइट मोड बंद है",
+        "FLIGHT_MODE_ON": "फ़्लाइट मोड चालू है",
+        "MODEM_INIT_ERROR": "मॉडेम आरंभीकरण विफल"
     }
 }

main/assets/locales/hr-HR/language.json

@@ -51,7 +51,9 @@
         "FOUND_NEW_ASSETS": "Pronađeni novi resursi: %s",
         "DOWNLOAD_ASSETS_FAILED": "Preuzimanje resursa nije uspjelo",
         "LOADING_ASSETS": "Učitavanje resursa...",
-        "HELLO_MY_FRIEND": "Bok, moj prijatelju!"
+        "HELLO_MY_FRIEND": "Bok, moj prijatelju!",
+        "FLIGHT_MODE_OFF": "Način rada u zrakoplovu je isključen",
+        "FLIGHT_MODE_ON": "Način rada u zrakoplovu je uključen",
+        "MODEM_INIT_ERROR": "Neuspjela inicijalizacija modema"
     }
-}
-
+}

main/assets/locales/hu-HU/language.json

@@ -51,7 +51,9 @@
         "FOUND_NEW_ASSETS": "Új erőforrások találva: %s",
         "DOWNLOAD_ASSETS_FAILED": "Az erőforrások letöltése sikertelen",
         "LOADING_ASSETS": "Erőforrások betöltése...",
-        "HELLO_MY_FRIEND": "Helló, barátom!"
+        "HELLO_MY_FRIEND": "Helló, barátom!",
+        "FLIGHT_MODE_OFF": "A repülési mód ki van kapcsolva",
+        "FLIGHT_MODE_ON": "A repülési mód be van kapcsolva",
+        "MODEM_INIT_ERROR": "A modem inicializálása sikertelen"
     }
-}
-
+}

main/assets/locales/id-ID/language.json

@@ -50,6 +50,10 @@
         "LOADING_ASSETS": "Memuat aset...",
         "PLEASE_WAIT": "Mohon tunggu...",
         "FOUND_NEW_ASSETS": "Ditemukan aset baru: %s",
-        "HELLO_MY_FRIEND": "Halo, teman saya!"
+        "HELLO_MY_FRIEND": "Halo, teman saya!",
+        "CONNECTION_SUCCESSFUL": "Koneksi berhasil",
+        "FLIGHT_MODE_OFF": "Mode pesawat nonaktif",
+        "FLIGHT_MODE_ON": "Mode pesawat aktif",
+        "MODEM_INIT_ERROR": "Gagal menginisialisasi modem"
     }
 }

main/assets/locales/it-IT/language.json

@@ -50,6 +50,10 @@
         "LOADING_ASSETS": "Caricamento risorse...",
         "PLEASE_WAIT": "Attendere prego...",
         "FOUND_NEW_ASSETS": "Trovate nuove risorse: %s",
-        "HELLO_MY_FRIEND": "Ciao, amico mio!"
+        "HELLO_MY_FRIEND": "Ciao, amico mio!",
+        "CONNECTION_SUCCESSFUL": "Connessione riuscita",
+        "FLIGHT_MODE_OFF": "La modalità aereo è disattivata",
+        "FLIGHT_MODE_ON": "La modalità aereo è attiva",
+        "MODEM_INIT_ERROR": "Inizializzazione modem non riuscita"
     }
 }

main/assets/locales/ja-JP/language.json

@@ -50,6 +50,10 @@
         "LOADING_ASSETS": "アセットを読み込み中...",
         "PLEASE_WAIT": "お待ちください...",
         "FOUND_NEW_ASSETS": "新しいアセットが見つかりました: %s",
-        "HELLO_MY_FRIEND": "こんにちは、友達！"
+        "HELLO_MY_FRIEND": "こんにちは、友達！",
+        "CONNECTION_SUCCESSFUL": "接続成功",
+        "FLIGHT_MODE_OFF": "機内モードがオフです",
+        "FLIGHT_MODE_ON": "機内モードがオンです",
+        "MODEM_INIT_ERROR": "モデムの初期化に失敗しました"
     }
 }

main/assets/locales/ko-KR/language.json

@@ -51,6 +51,9 @@
         "LOADING_ASSETS": "에셋 로딩 중...",
         "PLEASE_WAIT": "잠시 기다려 주세요...",
         "FOUND_NEW_ASSETS": "새로운 에셋을 발견했습니다: %s",
-        "HELLO_MY_FRIEND": "안녕하세요, 친구!"
+        "HELLO_MY_FRIEND": "안녕하세요, 친구!",
+        "FLIGHT_MODE_OFF": "비행기 모드가 꺼져 있습니다",
+        "FLIGHT_MODE_ON": "비행기 모드가 켜져 있습니다",
+        "MODEM_INIT_ERROR": "모뎀 초기화 실패"
     }
 }

main/assets/locales/ms-MY/language.json

@@ -51,7 +51,9 @@
         "FOUND_NEW_ASSETS": "Menemui aset baharu: %s",
         "DOWNLOAD_ASSETS_FAILED": "Gagal memuat turun aset",
         "LOADING_ASSETS": "Memuatkan aset...",
-        "HELLO_MY_FRIEND": "Hai, kawan saya!"
+        "HELLO_MY_FRIEND": "Hai, kawan saya!",
+        "FLIGHT_MODE_OFF": "Mod penerbangan dimatikan",
+        "FLIGHT_MODE_ON": "Mod penerbangan dihidupkan",
+        "MODEM_INIT_ERROR": "Modem gagal dimulakan"
     }
-}
-
+}

main/assets/locales/nb-NO/language.json

@@ -51,7 +51,9 @@
         "FOUND_NEW_ASSETS": "Fant nye ressurser: %s",
         "DOWNLOAD_ASSETS_FAILED": "Nedlasting av ressurser mislyktes",
         "LOADING_ASSETS": "Laster ressurser...",
-        "HELLO_MY_FRIEND": "Hei, min venn!"
+        "HELLO_MY_FRIEND": "Hei, min venn!",
+        "FLIGHT_MODE_OFF": "Flymodus er av",
+        "FLIGHT_MODE_ON": "Flymodus er på",
+        "MODEM_INIT_ERROR": "Modeminitialisering mislyktes"
     }
-}
-
+}

main/assets/locales/nl-NL/language.json

@@ -51,7 +51,9 @@
         "FOUND_NEW_ASSETS": "Nieuwe bronnen gevonden: %s",
         "DOWNLOAD_ASSETS_FAILED": "Downloaden van bronnen mislukt",
         "LOADING_ASSETS": "Bronnen laden...",
-        "HELLO_MY_FRIEND": "Hallo, mijn vriend!"
+        "HELLO_MY_FRIEND": "Hallo, mijn vriend!",
+        "FLIGHT_MODE_OFF": "Vliegtuigmodus is uitgeschakeld",
+        "FLIGHT_MODE_ON": "Vliegtuigmodus is ingeschakeld",
+        "MODEM_INIT_ERROR": "Modeminitialisatie mislukt"
     }
-}
-
+}

main/assets/locales/pl-PL/language.json

@@ -50,6 +50,10 @@
         "LOADING_ASSETS": "Ładowanie zasobów...",
         "PLEASE_WAIT": "Proszę czekać...",
         "FOUND_NEW_ASSETS": "Znaleziono nowe zasoby: %s",
-        "HELLO_MY_FRIEND": "Cześć, mój przyjacielu!"
+        "HELLO_MY_FRIEND": "Cześć, mój przyjacielu!",
+        "CONNECTION_SUCCESSFUL": "Połączenie udane",
+        "FLIGHT_MODE_OFF": "Tryb samolotowy jest wyłączony",
+        "FLIGHT_MODE_ON": "Tryb samolotowy jest włączony",
+        "MODEM_INIT_ERROR": "Inicjalizacja modemu nie powiodła się"
     }
 }

main/assets/locales/pt-PT/language.json

@@ -50,6 +50,10 @@
         "LOADING_ASSETS": "A carregar recursos...",
         "PLEASE_WAIT": "Por favor aguarde...",
         "FOUND_NEW_ASSETS": "Encontrados novos recursos: %s",
-        "HELLO_MY_FRIEND": "Olá, meu amigo!"
+        "HELLO_MY_FRIEND": "Olá, meu amigo!",
+        "CONNECTION_SUCCESSFUL": "Ligação bem-sucedida",
+        "FLIGHT_MODE_OFF": "O modo avião está desativado",
+        "FLIGHT_MODE_ON": "O modo avião está ativado",
+        "MODEM_INIT_ERROR": "Falha na inicialização do modem"
     }
 }

main/assets/locales/ro-RO/language.json

@@ -50,6 +50,10 @@
         "LOADING_ASSETS": "Se încarcă resursele...",
         "PLEASE_WAIT": "Vă rugăm să așteptați...",
         "FOUND_NEW_ASSETS": "S-au găsit resurse noi: %s",
-        "HELLO_MY_FRIEND": "Salut, prietenul meu!"
+        "HELLO_MY_FRIEND": "Salut, prietenul meu!",
+        "CONNECTION_SUCCESSFUL": "Conexiune reușită",
+        "FLIGHT_MODE_OFF": "Modul avion este dezactivat",
+        "FLIGHT_MODE_ON": "Modul avion este activat",
+        "MODEM_INIT_ERROR": "Inițializarea modemului a eșuat"
     }
 }

main/assets/locales/ru-RU/language.json

@@ -50,6 +50,10 @@
         "LOADING_ASSETS": "Загрузка ресурсов...",
         "PLEASE_WAIT": "Пожалуйста, подождите...",
         "FOUND_NEW_ASSETS": "Найдены новые ресурсы: %s",
-        "HELLO_MY_FRIEND": "Привет, мой друг!"
+        "HELLO_MY_FRIEND": "Привет, мой друг!",
+        "CONNECTION_SUCCESSFUL": "Подключение успешно",
+        "FLIGHT_MODE_OFF": "Режим полета выключен",
+        "FLIGHT_MODE_ON": "Режим полета включен",
+        "MODEM_INIT_ERROR": "Ошибка инициализации модема"
     }
 }

main/assets/locales/sk-SK/language.json

@@ -51,7 +51,9 @@
         "FOUND_NEW_ASSETS": "Nájdené nové zdroje: %s",
         "DOWNLOAD_ASSETS_FAILED": "Sťahovanie zdrojov zlyhalo",
         "LOADING_ASSETS": "Načítavanie zdrojov...",
-        "HELLO_MY_FRIEND": "Ahoj, môj priateľ!"
+        "HELLO_MY_FRIEND": "Ahoj, môj priateľ!",
+        "FLIGHT_MODE_OFF": "Letecký režim je vypnutý",
+        "FLIGHT_MODE_ON": "Letecký režim je zapnutý",
+        "MODEM_INIT_ERROR": "Chyba inicializácie modemu"
     }
-}
-
+}

main/assets/locales/sl-SI/language.json

@@ -51,7 +51,9 @@
         "FOUND_NEW_ASSETS": "Najdeni novi viri: %s",
         "DOWNLOAD_ASSETS_FAILED": "Prenos virov ni uspel",
         "LOADING_ASSETS": "Nalaganje virov...",
-        "HELLO_MY_FRIEND": "Pozdravljeni, moj prijatelj!"
+        "HELLO_MY_FRIEND": "Pozdravljeni, moj prijatelj!",
+        "FLIGHT_MODE_OFF": "Način leta je izklopljen",
+        "FLIGHT_MODE_ON": "Način leta je vklopljen",
+        "MODEM_INIT_ERROR": "Inicializacija modema ni uspela"
     }
-}
-
+}

main/assets/locales/sr-RS/language.json

@@ -51,7 +51,9 @@
         "FOUND_NEW_ASSETS": "Пронађени нови ресурси: %s",
         "DOWNLOAD_ASSETS_FAILED": "Преузимање ресурса није успело",
         "LOADING_ASSETS": "Учитавање ресурса...",
-        "HELLO_MY_FRIEND": "Здраво, пријатељу!"
+        "HELLO_MY_FRIEND": "Здраво, пријатељу!",
+        "FLIGHT_MODE_OFF": "Режим лета је искључен",
+        "FLIGHT_MODE_ON": "Режим лета је укључен",
+        "MODEM_INIT_ERROR": "Иницијализација модема није успела"
     }
-}
-
+}

main/assets/locales/sv-SE/language.json

@@ -51,7 +51,9 @@
         "FOUND_NEW_ASSETS": "Hittade nya resurser: %s",
         "DOWNLOAD_ASSETS_FAILED": "Nedladdning av resurser misslyckades",
         "LOADING_ASSETS": "Laddar resurser...",
-        "HELLO_MY_FRIEND": "Hej, min vän!"
+        "HELLO_MY_FRIEND": "Hej, min vän!",
+        "FLIGHT_MODE_OFF": "Flygläge är av",
+        "FLIGHT_MODE_ON": "Flygläge är på",
+        "MODEM_INIT_ERROR": "Modeminitiering misslyckades"
     }
-}
-
+}

main/assets/locales/th-TH/language.json

@@ -51,6 +51,9 @@
         "LOADING_ASSETS": "กำลังโหลดทรัพยากร...",
         "PLEASE_WAIT": "กรุณารอสักครู่...",
         "FOUND_NEW_ASSETS": "พบทรัพยากรใหม่: %s",
-        "HELLO_MY_FRIEND": "สวัสดี เพื่อนของฉัน!"
+        "HELLO_MY_FRIEND": "สวัสดี เพื่อนของฉัน!",
+        "FLIGHT_MODE_OFF": "โหมดเครื่องบินปิดอยู่",
+        "FLIGHT_MODE_ON": "โหมดเครื่องบินเปิดอยู่",
+        "MODEM_INIT_ERROR": "การเริ่มต้นโมเด็มล้มเหลว"
     }
 }

main/assets/locales/tr-TR/language.json

@@ -50,6 +50,10 @@
         "LOADING_ASSETS": "Varlıklar yükleniyor...",
         "PLEASE_WAIT": "Lütfen bekleyin...",
         "FOUND_NEW_ASSETS": "Yeni varlıklar bulundu: %s",
-        "HELLO_MY_FRIEND": "Merhaba, arkadaşım!"
+        "HELLO_MY_FRIEND": "Merhaba, arkadaşım!",
+        "CONNECTION_SUCCESSFUL": "Bağlantı başarılı",
+        "FLIGHT_MODE_OFF": "Uçak modu kapalı",
+        "FLIGHT_MODE_ON": "Uçak modu açık",
+        "MODEM_INIT_ERROR": "Modem başlatma hatası"
     }
 }

main/assets/locales/uk-UA/language.json

@@ -50,6 +50,10 @@
         "LOADING_ASSETS": "Завантаження ресурсів...",
         "PLEASE_WAIT": "Будь ласка, зачекайте...",
         "FOUND_NEW_ASSETS": "Знайдено нові ресурси: %s",
-        "HELLO_MY_FRIEND": "Привіт, мій друже!"
+        "HELLO_MY_FRIEND": "Привіт, мій друже!",
+        "CONNECTION_SUCCESSFUL": "Підключення успішне",
+        "FLIGHT_MODE_OFF": "Режим польоту вимкнено",
+        "FLIGHT_MODE_ON": "Режим польоту увімкнено",
+        "MODEM_INIT_ERROR": "Помилка ініціалізації модему"
     }
 }

main/assets/locales/vi-VN/language.json

@@ -51,6 +51,9 @@
         "LOADING_ASSETS": "Đang tải tài nguyên...",
         "PLEASE_WAIT": "Vui lòng đợi...",
         "FOUND_NEW_ASSETS": "Tìm thấy tài nguyên mới: %s",
-        "HELLO_MY_FRIEND": "Xin chào, bạn của tôi!"
+        "HELLO_MY_FRIEND": "Xin chào, bạn của tôi!",
+        "FLIGHT_MODE_OFF": "Chế độ máy bay đang tắt",
+        "FLIGHT_MODE_ON": "Chế độ máy bay đang bật",
+        "MODEM_INIT_ERROR": "Khởi tạo modem thất bại"
     }
 }

main/assets/locales/zh-CN/language.json

@@ -11,6 +11,7 @@
         "INITIALIZING": "正在初始化...",
         "PIN_ERROR": "请插入 SIM 卡",
         "REG_ERROR": "无法接入网络，请检查流量卡状态",
+        "MODEM_INIT_ERROR": "模组初始化失败",
         "DETECTING_MODULE": "检测模组...",
         "REGISTERING_NETWORK": "等待网络...",
         "CHECKING_NEW_VERSION": "检查新版本...",
@@ -50,6 +51,9 @@
         "LOADING_ASSETS": "加载资源...",
         "PLEASE_WAIT": "请稍候...",
         "FOUND_NEW_ASSETS": "发现新资源: %s",
-        "HELLO_MY_FRIEND": "你好，我的朋友！"
+        "HELLO_MY_FRIEND": "你好，我的朋友！",
+        "CONNECTION_SUCCESSFUL": "连接成功",
+        "FLIGHT_MODE_OFF": "飞行模式已关闭",
+        "FLIGHT_MODE_ON": "飞行模式已开启"
     }
 }

main/assets/locales/zh-TW/language.json

@@ -50,6 +50,10 @@
         "LOADING_ASSETS": "載入資源...",
         "PLEASE_WAIT": "請稍候...",
         "FOUND_NEW_ASSETS": "發現新資源: %s",
-        "HELLO_MY_FRIEND": "你好，我的朋友！"
+        "HELLO_MY_FRIEND": "你好，我的朋友！",
+        "CONNECTION_SUCCESSFUL": "連線成功",
+        "FLIGHT_MODE_OFF": "飛航模式已關閉",
+        "FLIGHT_MODE_ON": "飛航模式已開啟",
+        "MODEM_INIT_ERROR": "模組初始化失敗"
     }
 }

main/audio/audio_service.cc

@@ -2,6 +2,26 @@
 #include <esp_log.h>
 #include <cstring>
 
+#define RATE_CVT_CFG(_src_rate, _dest_rate, _channel)        \
+    (esp_ae_rate_cvt_cfg_t)                                  \
+    {                                                        \
+        .src_rate        = (uint32_t)(_src_rate),            \
+        .dest_rate       = (uint32_t)(_dest_rate),           \
+        .channel         = (uint8_t)(_channel),              \
+        .bits_per_sample = ESP_AUDIO_BIT16,                  \
+        .complexity      = 2,                                \
+        .perf_type       = ESP_AE_RATE_CVT_PERF_TYPE_SPEED,  \
+    }
+
+#define OPUS_DEC_CFG(_sample_rate, _frame_duration_ms)                                                    \
+    (esp_opus_dec_cfg_t)                                                                                  \
+    {                                                                                                     \
+        .sample_rate    = (uint32_t)(_sample_rate),                                                       \
+        .channel        = ESP_AUDIO_MONO,                                                                 \
+        .frame_duration = (esp_opus_dec_frame_duration_t)AS_OPUS_GET_FRAME_DRU_ENUM(_frame_duration_ms),  \
+        .self_delimited = false,                                                                          \
+    }
+
 #if CONFIG_USE_AUDIO_PROCESSOR
 #include "processors/afe_audio_processor.h"
 #else
@@ -17,7 +37,6 @@
 
 #define TAG "AudioService"
 
-
 AudioService::AudioService() {
     event_group_ = xEventGroupCreate();
 }
@@ -26,21 +45,51 @@ AudioService::~AudioService() {
     if (event_group_ != nullptr) {
         vEventGroupDelete(event_group_);
     }
+    if (opus_encoder_ != nullptr) {
+        esp_opus_enc_close(opus_encoder_);
+    }
+    if (opus_decoder_ != nullptr) {
+        esp_opus_dec_close(opus_decoder_);
+    }
+    if (input_resampler_ != nullptr) {
+        esp_ae_rate_cvt_close(input_resampler_);
+    }
+    if (output_resampler_ != nullptr) {
+        esp_ae_rate_cvt_close(output_resampler_);
+    }
 }
 
-
 void AudioService::Initialize(AudioCodec* codec) {
     codec_ = codec;
     codec_->Start();
 
-    /* Setup the audio codec */
-    opus_decoder_ = std::make_unique<OpusDecoderWrapper>(codec->output_sample_rate(), 1, OPUS_FRAME_DURATION_MS);
-    opus_encoder_ = std::make_unique<OpusEncoderWrapper>(16000, 1, OPUS_FRAME_DURATION_MS);
-    opus_encoder_->SetComplexity(0);
+    esp_opus_dec_cfg_t opus_dec_cfg = OPUS_DEC_CFG(codec->output_sample_rate(), OPUS_FRAME_DURATION_MS);
+    auto ret = esp_opus_dec_open(&opus_dec_cfg, sizeof(esp_opus_dec_cfg_t), &opus_decoder_);
+    if (opus_decoder_ == nullptr) {
+        ESP_LOGE(TAG, "Failed to create audio decoder, error code: %d", ret);
+    } else {
+        decoder_sample_rate_ = codec->output_sample_rate();
+        decoder_duration_ms_ = OPUS_FRAME_DURATION_MS;
+        decoder_frame_size_ = decoder_sample_rate_ / 1000 * OPUS_FRAME_DURATION_MS;
+    }
+    esp_opus_enc_config_t opus_enc_cfg = AS_OPUS_ENC_CONFIG();
+    ret = esp_opus_enc_open(&opus_enc_cfg, sizeof(esp_opus_enc_config_t), &opus_encoder_);
+    if (opus_encoder_ == nullptr) {
+        ESP_LOGE(TAG, "Failed to create audio encoder, error code: %d", ret);
+    } else {
+        encoder_sample_rate_ = 16000;
+        encoder_duration_ms_ = OPUS_FRAME_DURATION_MS;
+        esp_opus_enc_get_frame_size(opus_encoder_, &encoder_frame_size_, &encoder_outbuf_size_);
+        encoder_frame_size_ = encoder_frame_size_ / sizeof(int16_t);
+    }
 
     if (codec->input_sample_rate() != 16000) {
-        input_resampler_.Configure(codec->input_sample_rate(), 16000);
-        reference_resampler_.Configure(codec->input_sample_rate(), 16000);
+        esp_ae_rate_cvt_cfg_t input_resampler_cfg = RATE_CVT_CFG(
+            codec->input_sample_rate(), ESP_AUDIO_SAMPLE_RATE_16K, codec->input_channels());
+        auto resampler_ret = esp_ae_rate_cvt_open(&input_resampler_cfg, &input_resampler_);
+        if (input_resampler_ == nullptr) {
+            ESP_LOGE(TAG, "Failed to create input resampler, error code: %d", resampler_ret);
+        }
     }
 
 #if CONFIG_USE_AUDIO_PROCESSOR
@@ -114,7 +163,7 @@ void AudioService::Start() {
         AudioService* audio_service = (AudioService*)arg;
         audio_service->OpusCodecTask();
         vTaskDelete(NULL);
-    }, "opus_codec", 2048 * 13, this, 2, &opus_codec_task_handle_);
+    }, "opus_codec", 2048 * 12, this, 2, &opus_codec_task_handle_);
 }
 
 void AudioService::Stop() {
@@ -144,25 +193,16 @@ bool AudioService::ReadAudioData(std::vector<int16_t>& data, int sample_rate, in
         if (!codec_->InputData(data)) {
             return false;
         }
-        if (codec_->input_channels() == 2) {
-            auto mic_channel = std::vector<int16_t>(data.size() / 2);
-            auto reference_channel = std::vector<int16_t>(data.size() / 2);
-            for (size_t i = 0, j = 0; i < mic_channel.size(); ++i, j += 2) {
-                mic_channel[i] = data[j];
-                reference_channel[i] = data[j + 1];
-            }
-            auto resampled_mic = std::vector<int16_t>(input_resampler_.GetOutputSamples(mic_channel.size()));
-            auto resampled_reference = std::vector<int16_t>(reference_resampler_.GetOutputSamples(reference_channel.size()));
-            input_resampler_.Process(mic_channel.data(), mic_channel.size(), resampled_mic.data());
-            reference_resampler_.Process(reference_channel.data(), reference_channel.size(), resampled_reference.data());
-            data.resize(resampled_mic.size() + resampled_reference.size());
-            for (size_t i = 0, j = 0; i < resampled_mic.size(); ++i, j += 2) {
-                data[j] = resampled_mic[i];
-                data[j + 1] = resampled_reference[i];
-            }
-        } else {
-            auto resampled = std::vector<int16_t>(input_resampler_.GetOutputSamples(data.size()));
-            input_resampler_.Process(data.data(), data.size(), resampled.data());
+        if (input_resampler_ != nullptr) {
+            std::lock_guard<std::mutex> lock(input_resampler_mutex_);
+            uint32_t in_sample_num = data.size() / codec_->input_channels();
+            uint32_t output_samples = 0;
+            esp_ae_rate_cvt_get_max_out_sample_num(input_resampler_, in_sample_num, &output_samples);
+            auto resampled = std::vector<int16_t>(output_samples * codec_->input_channels());
+            uint32_t actual_output = output_samples;
+            esp_ae_rate_cvt_process(input_resampler_, (esp_ae_sample_t)data.data(), in_sample_num,
+                                   (esp_ae_sample_t)resampled.data(), &actual_output);
+            resampled.resize(actual_output * codec_->input_channels());
             data = std::move(resampled);
         }
     } else {
@@ -225,27 +265,18 @@ void AudioService::AudioInputTask() {
             }
         }
 
-        /* Feed the wake word */
-        if (bits & AS_EVENT_WAKE_WORD_RUNNING) {
+        /* Feed the wake word and/or audio processor */
+        if (bits & (AS_EVENT_WAKE_WORD_RUNNING | AS_EVENT_AUDIO_PROCESSOR_RUNNING)) {
+            int samples = 160; // 10ms
             std::vector<int16_t> data;
-            int samples = wake_word_->GetFeedSize();
-            if (samples > 0) {
-                if (ReadAudioData(data, 16000, samples)) {
+            if (ReadAudioData(data, 16000, samples)) {
+                if (bits & AS_EVENT_WAKE_WORD_RUNNING) {
                     wake_word_->Feed(data);
-                    continue;
                 }
-            }
-        }
-
-        /* Feed the audio processor */
-        if (bits & AS_EVENT_AUDIO_PROCESSOR_RUNNING) {
-            std::vector<int16_t> data;
-            int samples = audio_processor_->GetFeedSize();
-            if (samples > 0) {
-                if (ReadAudioData(data, 16000, samples)) {
+                if (bits & AS_EVENT_AUDIO_PROCESSOR_RUNNING) {
                     audio_processor_->Feed(std::move(data));
-                    continue;
                 }
+                continue;
             }
         }
 
@@ -316,25 +347,49 @@ void AudioService::OpusCodecTask() {
             task->timestamp = packet->timestamp;
 
             SetDecodeSampleRate(packet->sample_rate, packet->frame_duration);
-            if (opus_decoder_->Decode(std::move(packet->payload), task->pcm)) {
-                // Resample if the sample rate is different
-                if (opus_decoder_->sample_rate() != codec_->output_sample_rate()) {
-                    int target_size = output_resampler_.GetOutputSamples(task->pcm.size());
-                    std::vector<int16_t> resampled(target_size);
-                    output_resampler_.Process(task->pcm.data(), task->pcm.size(), resampled.data());
-                    task->pcm = std::move(resampled);
+            if (opus_decoder_ != nullptr) {
+                task->pcm.resize(decoder_frame_size_);
+                esp_audio_dec_in_raw_t raw = {
+                    .buffer = (uint8_t *)(packet->payload.data()),
+                    .len = (uint32_t)(packet->payload.size()),
+                    .consumed = 0,
+                    .frame_recover = ESP_AUDIO_DEC_RECOVERY_NONE,
+                };
+                esp_audio_dec_out_frame_t out_frame = {
+                    .buffer = (uint8_t *)(task->pcm.data()),
+                    .len = (uint32_t)(task->pcm.size() * sizeof(int16_t)),
+                    .decoded_size = 0,
+                };
+                esp_audio_dec_info_t dec_info = {};
+                std::unique_lock<std::mutex> decoder_lock(decoder_mutex_);
+                auto ret = esp_opus_dec_decode(opus_decoder_, &raw, &out_frame, &dec_info);
+                decoder_lock.unlock();
+                if (ret == ESP_AUDIO_ERR_OK) {
+                    task->pcm.resize(out_frame.decoded_size / sizeof(int16_t));
+                    if (decoder_sample_rate_ != codec_->output_sample_rate() && output_resampler_ != nullptr) {
+                        uint32_t target_size = 0;
+                        esp_ae_rate_cvt_get_max_out_sample_num(output_resampler_, task->pcm.size(), &target_size);
+                        std::vector<int16_t> resampled(target_size);
+                        uint32_t actual_output = target_size;
+                        esp_ae_rate_cvt_process(output_resampler_, (esp_ae_sample_t)task->pcm.data(), task->pcm.size(),
+                                                (esp_ae_sample_t)resampled.data(), &actual_output);
+                        resampled.resize(actual_output);
+                        task->pcm = std::move(resampled);
+                    }
+                    lock.lock();
+                    audio_playback_queue_.push_back(std::move(task));
+                    audio_queue_cv_.notify_all();
+                    debug_statistics_.decode_count++;
+                } else {
+                    ESP_LOGE(TAG, "Failed to decode audio after resize, error code: %d", ret);
+                    lock.lock();
                 }
-
-                lock.lock();
-                audio_playback_queue_.push_back(std::move(task));
-                audio_queue_cv_.notify_all();
             } else {
-                ESP_LOGE(TAG, "Failed to decode audio");
+                ESP_LOGE(TAG, "Audio decoder is not configured");
                 lock.lock();
             }
             debug_statistics_.decode_count++;
         }
-        
         /* Encode the audio to send queue */
         if (!audio_encode_queue_.empty() && audio_send_queue_.size() < MAX_SEND_PACKETS_IN_QUEUE) {
             auto task = std::move(audio_encode_queue_.front());
@@ -346,24 +401,42 @@ void AudioService::OpusCodecTask() {
             packet->frame_duration = OPUS_FRAME_DURATION_MS;
             packet->sample_rate = 16000;
             packet->timestamp = task->timestamp;
-            if (!opus_encoder_->Encode(std::move(task->pcm), packet->payload)) {
-                ESP_LOGE(TAG, "Failed to encode audio");
-                continue;
-            }
 
-            if (task->type == kAudioTaskTypeEncodeToSendQueue) {
-                {
-                    std::lock_guard<std::mutex> lock(audio_queue_mutex_);
-                    audio_send_queue_.push_back(std::move(packet));
+            if (opus_encoder_ != nullptr && task->pcm.size() == encoder_frame_size_) {
+                std::vector<uint8_t> buf(encoder_outbuf_size_);
+                esp_audio_enc_in_frame_t in = {
+                    .buffer = (uint8_t *)(task->pcm.data()),
+                    .len = (uint32_t)(encoder_frame_size_ * sizeof(int16_t)),
+                };
+                esp_audio_enc_out_frame_t out = {
+                    .buffer = buf.data(),
+                    .len = (uint32_t)encoder_outbuf_size_,
+                    .encoded_bytes = 0,
+                };
+                auto ret = esp_opus_enc_process(opus_encoder_, &in, &out);
+                if (ret == ESP_AUDIO_ERR_OK) {
+                    packet->payload.assign(buf.data(), buf.data() + out.encoded_bytes);
+
+                    if (task->type == kAudioTaskTypeEncodeToSendQueue) {
+                        {
+                            std::lock_guard<std::mutex> lock2(audio_queue_mutex_);
+                            audio_send_queue_.push_back(std::move(packet));
+                        }
+                        if (callbacks_.on_send_queue_available) {
+                            callbacks_.on_send_queue_available();
+                        }
+                    } else if (task->type == kAudioTaskTypeEncodeToTestingQueue) {
+                        std::lock_guard<std::mutex> lock2(audio_queue_mutex_);
+                        audio_testing_queue_.push_back(std::move(packet));
+                    }
+                    debug_statistics_.encode_count++;
+                } else {
+                    ESP_LOGE(TAG, "Failed to encode audio, error code: %d", ret);
                 }
-                if (callbacks_.on_send_queue_available) {
-                    callbacks_.on_send_queue_available();
-                }
-            } else if (task->type == kAudioTaskTypeEncodeToTestingQueue) {
-                std::lock_guard<std::mutex> lock(audio_queue_mutex_);
-                audio_testing_queue_.push_back(std::move(packet));
+            } else {
+                ESP_LOGE(TAG, "Failed to encode audio: encoder not configured or invalid frame size (got %u, expected %u)",
+                         task->pcm.size(), encoder_frame_size_);
             }
-            debug_statistics_.encode_count++;
             lock.lock();
         }
     }
@@ -372,17 +445,38 @@ void AudioService::OpusCodecTask() {
 }
 
 void AudioService::SetDecodeSampleRate(int sample_rate, int frame_duration) {
-    if (opus_decoder_->sample_rate() == sample_rate && opus_decoder_->duration_ms() == frame_duration) {
+    if (decoder_sample_rate_ == sample_rate && decoder_duration_ms_ == frame_duration) {
         return;
     }
-
-    opus_decoder_.reset();
-    opus_decoder_ = std::make_unique<OpusDecoderWrapper>(sample_rate, 1, frame_duration);
+    std::unique_lock<std::mutex> decoder_lock(decoder_mutex_);
+    if (opus_decoder_ != nullptr) {
+        esp_opus_dec_close(opus_decoder_);
+        opus_decoder_ = nullptr;
+    }
+    decoder_lock.unlock();
+    esp_opus_dec_cfg_t opus_dec_cfg = OPUS_DEC_CFG(sample_rate, frame_duration);
+    auto ret = esp_opus_dec_open(&opus_dec_cfg, sizeof(esp_opus_dec_cfg_t), &opus_decoder_);
+    if (opus_decoder_ == nullptr) {
+        ESP_LOGE(TAG, "Failed to create audio decoder, error code: %d", ret);
+        return;
+    }
+    decoder_sample_rate_ = sample_rate;
+    decoder_duration_ms_ = frame_duration;
+    decoder_frame_size_ = decoder_sample_rate_ / 1000 * frame_duration;
 
     auto codec = Board::GetInstance().GetAudioCodec();
-    if (opus_decoder_->sample_rate() != codec->output_sample_rate()) {
-        ESP_LOGI(TAG, "Resampling audio from %d to %d", opus_decoder_->sample_rate(), codec->output_sample_rate());
-        output_resampler_.Configure(opus_decoder_->sample_rate(), codec->output_sample_rate());
+    if (decoder_sample_rate_ != codec->output_sample_rate()) {
+        ESP_LOGI(TAG, "Resampling audio from %d to %d", decoder_sample_rate_, codec->output_sample_rate());
+        if (output_resampler_ != nullptr) {
+            esp_ae_rate_cvt_close(output_resampler_);
+            output_resampler_ = nullptr;
+        }
+        esp_ae_rate_cvt_cfg_t output_resampler_cfg = RATE_CVT_CFG(
+            decoder_sample_rate_, codec->output_sample_rate(), ESP_AUDIO_MONO);
+        auto resampler_ret = esp_ae_rate_cvt_open(&output_resampler_cfg, &output_resampler_);
+        if (output_resampler_ == nullptr) {
+            ESP_LOGE(TAG, "Failed to create output resampler, error code: %d", resampler_ret);
+        }
     }
 }
 
@@ -390,7 +484,6 @@ void AudioService::PushTaskToEncodeQueue(AudioTaskType type, std::vector<int16_t
     auto task = std::make_unique<AudioTask>();
     task->type = type;
     task->pcm = std::move(pcm);
-    
     /* Push the task to the encode queue */
     std::unique_lock<std::mutex> lock(audio_queue_mutex_);
 
@@ -466,6 +559,14 @@ void AudioService::EnableWakeWordDetection(bool enable) {
             }
             wake_word_initialized_ = true;
         }
+        // Reset input resampler to clear cached data from previous mode (e.g. AudioProcessor)
+        // This prevents buffer overflow when switching between different feed sizes
+        {
+            std::lock_guard<std::mutex> lock(input_resampler_mutex_);
+            if (input_resampler_ != nullptr) {
+                esp_ae_rate_cvt_reset(input_resampler_);
+            }
+        }
         wake_word_->Start();
         xEventGroupSetBits(event_group_, AS_EVENT_WAKE_WORD_RUNNING);
     } else {
@@ -485,6 +586,14 @@ void AudioService::EnableVoiceProcessing(bool enable) {
         /* We should make sure no audio is playing */
         ResetDecoder();
         audio_input_need_warmup_ = true;
+        // Reset input resampler to clear cached data from previous mode (e.g. WakeWord)
+        // This prevents buffer overflow when switching between different feed sizes
+        {
+            std::lock_guard<std::mutex> lock(input_resampler_mutex_);
+            if (input_resampler_ != nullptr) {
+                esp_ae_rate_cvt_reset(input_resampler_);
+            }
+        }
         audio_processor_->Start();
         xEventGroupSetBits(event_group_, AS_EVENT_AUDIO_PROCESSOR_RUNNING);
     } else {
@@ -580,18 +689,16 @@ void AudioService::PlaySound(const std::string_view& ogg) {
                 // 解析OpusHead包
                 if (pkt_len >= 19 && std::memcmp(pkt_ptr, "OpusHead", 8) == 0) {
                     seen_head = true;
-                    
                     // OpusHead结构：[0-7] "OpusHead", [8] version, [9] channel_count, [10-11] pre_skip
                     // [12-15] input_sample_rate, [16-17] output_gain, [18] mapping_family
                     if (pkt_len >= 12) {
                         uint8_t version = pkt_ptr[8];
                         uint8_t channel_count = pkt_ptr[9];
-                        
                         if (pkt_len >= 16) {
                             // 读取输入采样率 (little-endian)
-                            sample_rate = pkt_ptr[12] | (pkt_ptr[13] << 8) | 
+                            sample_rate = pkt_ptr[12] | (pkt_ptr[13] << 8) |
                                         (pkt_ptr[14] << 16) | (pkt_ptr[15] << 24);
-                            ESP_LOGI(TAG, "OpusHead: version=%d, channels=%d, sample_rate=%d", 
+                            ESP_LOGI(TAG, "OpusHead: version=%d, channels=%d, sample_rate=%d",
                                    version, channel_count, sample_rate);
                         }
                     }
@@ -624,9 +731,20 @@ bool AudioService::IsIdle() {
     return audio_encode_queue_.empty() && audio_decode_queue_.empty() && audio_playback_queue_.empty() && audio_testing_queue_.empty();
 }
 
+void AudioService::WaitForPlaybackQueueEmpty() {
+    std::unique_lock<std::mutex> lock(audio_queue_mutex_);
+    audio_queue_cv_.wait(lock, [this]() { 
+        return service_stopped_ || (audio_decode_queue_.empty() && audio_playback_queue_.empty()); 
+    });
+}
+
 void AudioService::ResetDecoder() {
     std::lock_guard<std::mutex> lock(audio_queue_mutex_);
-    opus_decoder_->ResetState();
+    std::unique_lock<std::mutex> decoder_lock(decoder_mutex_);
+    if (opus_decoder_ != nullptr) {
+        esp_opus_dec_reset(opus_decoder_);
+    }
+    decoder_lock.unlock();
     timestamp_queue_.clear();
     audio_decode_queue_.clear();
     audio_playback_queue_.clear();

main/audio/audio_service.h

@@ -12,10 +12,11 @@
 #include <freertos/event_groups.h>
 #include <esp_timer.h>
 #include <model_path.h>
-
-#include <opus_encoder.h>
-#include <opus_decoder.h>
-#include <opus_resampler.h>
+#include "esp_audio_enc.h"
+#include "esp_opus_enc.h"
+#include "esp_opus_dec.h"
+#include "esp_ae_rate_cvt.h"
+#include "esp_audio_types.h"
 
 #include "audio_codec.h"
 #include "audio_processor.h"
@@ -46,12 +47,34 @@
 #define AUDIO_POWER_TIMEOUT_MS 15000
 #define AUDIO_POWER_CHECK_INTERVAL_MS 1000
 
-
 #define AS_EVENT_AUDIO_TESTING_RUNNING      (1 << 0)
 #define AS_EVENT_WAKE_WORD_RUNNING          (1 << 1)
 #define AS_EVENT_AUDIO_PROCESSOR_RUNNING    (1 << 2)
 #define AS_EVENT_PLAYBACK_NOT_EMPTY         (1 << 3)
 
+#define AS_OPUS_GET_FRAME_DRU_ENUM(duration_ms)                   \
+    ((duration_ms) == 5 ? ESP_OPUS_ENC_FRAME_DURATION_5_MS :      \
+     (duration_ms) == 10 ? ESP_OPUS_ENC_FRAME_DURATION_10_MS :    \
+     (duration_ms) == 20 ? ESP_OPUS_ENC_FRAME_DURATION_20_MS :    \
+     (duration_ms) == 40 ? ESP_OPUS_ENC_FRAME_DURATION_40_MS :    \
+     (duration_ms) == 60 ? ESP_OPUS_ENC_FRAME_DURATION_60_MS :    \
+     (duration_ms) == 80 ? ESP_OPUS_ENC_FRAME_DURATION_80_MS :    \
+     (duration_ms) == 100 ? ESP_OPUS_ENC_FRAME_DURATION_100_MS :  \
+     (duration_ms) == 120 ? ESP_OPUS_ENC_FRAME_DURATION_120_MS : -1)
+
+#define AS_OPUS_ENC_CONFIG() {                                                                                    \
+        .sample_rate        = ESP_AUDIO_SAMPLE_RATE_16K,                                                          \
+        .channel            = ESP_AUDIO_MONO,                                                                     \
+        .bits_per_sample    = ESP_AUDIO_BIT16,                                                                    \
+        .bitrate            = ESP_OPUS_BITRATE_AUTO,                                                              \
+        .frame_duration     = (esp_opus_enc_frame_duration_t)AS_OPUS_GET_FRAME_DRU_ENUM(OPUS_FRAME_DURATION_MS),  \
+        .application_mode   = ESP_OPUS_ENC_APPLICATION_AUDIO,                                                     \
+        .complexity         = 0,                                                                                  \
+        .enable_fec         = false,                                                                              \
+        .enable_dtx         = true,                                                                               \
+        .enable_vbr         = true,                                                                               \
+    }
+
 struct AudioServiceCallbacks {
     std::function<void(void)> on_send_queue_available;
     std::function<void(const std::string&)> on_wake_word_detected;
@@ -92,6 +115,7 @@ public:
     const std::string& GetLastWakeWord() const;
     bool IsVoiceDetected() const { return voice_detected_; }
     bool IsIdle();
+    void WaitForPlaybackQueueEmpty();
     bool IsWakeWordRunning() const { return xEventGroupGetBits(event_group_) & AS_EVENT_WAKE_WORD_RUNNING; }
     bool IsAudioProcessorRunning() const { return xEventGroupGetBits(event_group_) & AS_EVENT_AUDIO_PROCESSOR_RUNNING; }
     bool IsAfeWakeWord();
@@ -116,11 +140,21 @@ private:
     std::unique_ptr<AudioProcessor> audio_processor_;
     std::unique_ptr<WakeWord> wake_word_;
     std::unique_ptr<AudioDebugger> audio_debugger_;
-    std::unique_ptr<OpusEncoderWrapper> opus_encoder_;
-    std::unique_ptr<OpusDecoderWrapper> opus_decoder_;
-    OpusResampler input_resampler_;
-    OpusResampler reference_resampler_;
-    OpusResampler output_resampler_;
+    void* opus_encoder_ = nullptr;
+    void* opus_decoder_ = nullptr;
+    std::mutex decoder_mutex_;
+    std::mutex input_resampler_mutex_;
+    esp_ae_rate_cvt_handle_t input_resampler_ = nullptr;
+    esp_ae_rate_cvt_handle_t output_resampler_ = nullptr;
+    
+    // Encoder/Decoder state
+    int encoder_sample_rate_ = 16000;
+    int encoder_duration_ms_ = OPUS_FRAME_DURATION_MS;
+    int encoder_frame_size_ = 0;
+    int encoder_outbuf_size_ = 0;
+    int decoder_sample_rate_ = 0;
+    int decoder_duration_ms_ = OPUS_FRAME_DURATION_MS;
+    int decoder_frame_size_ = 0;
     DebugStatistics debug_statistics_;
     srmodel_list_t* models_list_ = nullptr;
 

main/audio/processors/afe_audio_processor.cc

@@ -92,7 +92,18 @@ void AfeAudioProcessor::Feed(std::vector<int16_t>&& data) {
     if (afe_data_ == nullptr) {
         return;
     }
-    afe_iface_->feed(afe_data_, data.data());
+
+    std::lock_guard<std::mutex> lock(input_buffer_mutex_);
+    // Check running state inside lock to avoid TOCTOU race with Stop()
+    if (!IsRunning()) {
+        return;
+    }
+    input_buffer_.insert(input_buffer_.end(), data.begin(), data.end());
+    size_t chunk_size = afe_iface_->get_feed_chunksize(afe_data_) * codec_->input_channels();
+    while (input_buffer_.size() >= chunk_size) {
+        afe_iface_->feed(afe_data_, input_buffer_.data());
+        input_buffer_.erase(input_buffer_.begin(), input_buffer_.begin() + chunk_size);
+    }
 }
 
 void AfeAudioProcessor::Start() {
@@ -101,9 +112,12 @@ void AfeAudioProcessor::Start() {
 
 void AfeAudioProcessor::Stop() {
     xEventGroupClearBits(event_group_, PROCESSOR_RUNNING);
+
+    std::lock_guard<std::mutex> lock(input_buffer_mutex_);
     if (afe_data_ != nullptr) {
         afe_iface_->reset_buffer(afe_data_);
     }
+    input_buffer_.clear();
 }
 
 bool AfeAudioProcessor::IsRunning() {

main/audio/processors/afe_audio_processor.h

@@ -9,6 +9,7 @@
 #include <string>
 #include <vector>
 #include <functional>
+#include <mutex>
 
 #include "audio_processor.h"
 #include "audio_codec.h"
@@ -37,6 +38,8 @@ private:
     AudioCodec* codec_ = nullptr;
     int frame_samples_ = 0;
     bool is_speaking_ = false;
+    std::vector<int16_t> input_buffer_;
+    std::mutex input_buffer_mutex_;
     std::vector<int16_t> output_buffer_;
 
     void AudioProcessorTask();

main/audio/processors/no_audio_processor.h

@@ -3,6 +3,7 @@
 
 #include <vector>
 #include <functional>
+#include <atomic>
 
 #include "audio_processor.h"
 #include "audio_codec.h"
@@ -27,7 +28,7 @@ private:
     int frame_samples_ = 0;
     std::function<void(std::vector<int16_t>&& data)> output_callback_;
     std::function<void(bool speaking)> vad_state_change_callback_;
-    bool is_running_ = false;
+    std::atomic<bool> is_running_ = false;
 };
 
 #endif 

main/audio/wake_words/afe_wake_word.cc

@@ -1,6 +1,5 @@
 #include "afe_wake_word.h"
 #include "audio_service.h"
-
 #include <esp_log.h>
 #include <sstream>
 
@@ -100,16 +99,30 @@ void AfeWakeWord::Start() {
 
 void AfeWakeWord::Stop() {
     xEventGroupClearBits(event_group_, DETECTION_RUNNING_EVENT);
+
+    std::lock_guard<std::mutex> lock(input_buffer_mutex_);
     if (afe_data_ != nullptr) {
         afe_iface_->reset_buffer(afe_data_);
     }
+    input_buffer_.clear();
 }
 
 void AfeWakeWord::Feed(const std::vector<int16_t>& data) {
     if (afe_data_ == nullptr) {
         return;
     }
-    afe_iface_->feed(afe_data_, data.data());
+
+    std::lock_guard<std::mutex> lock(input_buffer_mutex_);
+    // Check running state inside lock to avoid TOCTOU race with Stop()
+    if (!(xEventGroupGetBits(event_group_) & DETECTION_RUNNING_EVENT)) {
+        return;
+    }
+    input_buffer_.insert(input_buffer_.end(), data.begin(), data.end());
+    size_t chunk_size = afe_iface_->get_feed_chunksize(afe_data_) * codec_->input_channels();
+    while (input_buffer_.size() >= chunk_size) {
+        afe_iface_->feed(afe_data_, input_buffer_.data());
+        input_buffer_.erase(input_buffer_.begin(), input_buffer_.begin() + chunk_size);
+    }
 }
 
 size_t AfeWakeWord::GetFeedSize() {
@@ -157,7 +170,7 @@ void AfeWakeWord::StoreWakeWordData(const int16_t* data, size_t samples) {
 }
 
 void AfeWakeWord::EncodeWakeWordData() {
-    const size_t stack_size = 4096 * 7;
+    const size_t stack_size = 4096 * 6;
     wake_word_opus_.clear();
     if (wake_word_encode_task_stack_ == nullptr) {
         wake_word_encode_task_stack_ = (StackType_t*)heap_caps_malloc(stack_size, MALLOC_CAP_SPIRAM);
@@ -172,20 +185,62 @@ void AfeWakeWord::EncodeWakeWordData() {
         auto this_ = (AfeWakeWord*)arg;
         {
             auto start_time = esp_timer_get_time();
-            auto encoder = std::make_unique<OpusEncoderWrapper>(16000, 1, OPUS_FRAME_DURATION_MS);
-            encoder->SetComplexity(0); // 0 is the fastest
-
+            // Create encoder
+            esp_opus_enc_config_t opus_enc_cfg = AS_OPUS_ENC_CONFIG();
+            void* encoder_handle = nullptr;
+            auto ret = esp_opus_enc_open(&opus_enc_cfg, sizeof(esp_opus_enc_config_t), &encoder_handle);
+            if (encoder_handle == nullptr) {
+                ESP_LOGE(TAG, "Failed to create audio encoder, error code: %d", ret);
+                std::lock_guard<std::mutex> lock(this_->wake_word_mutex_);
+                this_->wake_word_opus_.push_back(std::vector<uint8_t>());
+                this_->wake_word_cv_.notify_all();
+                return;
+            }
+            
+            // Get frame size
+            int frame_size = 0;
+            int outbuf_size = 0;
+            esp_opus_enc_get_frame_size(encoder_handle, &frame_size, &outbuf_size);
+            frame_size = frame_size / sizeof(int16_t);
+            
+            // Encode all PCM data
             int packets = 0;
+            std::vector<int16_t> in_buffer;
+            esp_audio_enc_in_frame_t in = {};
+            esp_audio_enc_out_frame_t out = {};
+            
             for (auto& pcm: this_->wake_word_pcm_) {
-                encoder->Encode(std::move(pcm), [this_](std::vector<uint8_t>&& opus) {
-                    std::lock_guard<std::mutex> lock(this_->wake_word_mutex_);
-                    this_->wake_word_opus_.emplace_back(std::move(opus));
-                    this_->wake_word_cv_.notify_all();
-                });
-                packets++;
+                if (in_buffer.empty()) {
+                    in_buffer = std::move(pcm);
+                } else {
+                    in_buffer.reserve(in_buffer.size() + pcm.size());
+                    in_buffer.insert(in_buffer.end(), pcm.begin(), pcm.end());
+                }
+                
+                while (in_buffer.size() >= frame_size) {
+                    std::vector<uint8_t> opus_buf(outbuf_size);
+                    in.buffer = (uint8_t *)(in_buffer.data());
+                    in.len = (uint32_t)(frame_size * sizeof(int16_t));
+                    out.buffer = opus_buf.data();
+                    out.len = outbuf_size;
+                    out.encoded_bytes = 0;
+                    
+                    ret = esp_opus_enc_process(encoder_handle, &in, &out);
+                    if (ret == ESP_AUDIO_ERR_OK) {
+                        std::lock_guard<std::mutex> lock(this_->wake_word_mutex_);
+                        this_->wake_word_opus_.emplace_back(opus_buf.data(), opus_buf.data() + out.encoded_bytes);
+                        this_->wake_word_cv_.notify_all();
+                        packets++;
+                    } else {
+                        ESP_LOGE(TAG, "Failed to encode audio, error code: %d", ret);
+                    }
+                    
+                    in_buffer.erase(in_buffer.begin(), in_buffer.begin() + frame_size);
+                }
             }
             this_->wake_word_pcm_.clear();
-
+            // Close encoder
+            esp_opus_enc_close(encoder_handle);
             auto end_time = esp_timer_get_time();
             ESP_LOGI(TAG, "Encode wake word opus %d packets in %ld ms", packets, (long)((end_time - start_time) / 1000));
 

main/audio/wake_words/afe_wake_word.h

@@ -44,6 +44,8 @@ private:
     std::function<void(const std::string& wake_word)> wake_word_detected_callback_;
     AudioCodec* codec_ = nullptr;
     std::string last_detected_wake_word_;
+    std::vector<int16_t> input_buffer_;
+    std::mutex input_buffer_mutex_;
 
     TaskHandle_t wake_word_encode_task_ = nullptr;
     StaticTask_t* wake_word_encode_task_buffer_ = nullptr;

main/audio/wake_words/custom_wake_word.cc

@@ -9,10 +9,8 @@
 #include <esp_mn_speech_commands.h>
 #include <cJSON.h>
 
-
 #define TAG "CustomWakeWord"
 
-
 CustomWakeWord::CustomWakeWord()
     : wake_word_pcm_(), wake_word_opus_() {
 }
@@ -140,49 +138,64 @@ void CustomWakeWord::Start() {
 
 void CustomWakeWord::Stop() {
     running_ = false;
+
+    std::lock_guard<std::mutex> lock(input_buffer_mutex_);
+    input_buffer_.clear();
 }
 
 void CustomWakeWord::Feed(const std::vector<int16_t>& data) {
-    if (multinet_model_data_ == nullptr || !running_) {
+    if (multinet_model_data_ == nullptr) {
+        return;
+    }
+
+    std::lock_guard<std::mutex> lock(input_buffer_mutex_);
+    // Check running state inside lock to avoid TOCTOU race with Stop()
+    if (!running_) {
         return;
     }
 
-    esp_mn_state_t mn_state;
     // If input channels is 2, we need to fetch the left channel data
     if (codec_->input_channels() == 2) {
-        auto mono_data = std::vector<int16_t>(data.size() / 2);
-        for (size_t i = 0, j = 0; i < mono_data.size(); ++i, j += 2) {
-            mono_data[i] = data[j];
+        for (size_t i = 0; i < data.size(); i += 2) {
+            input_buffer_.push_back(data[i]);
         }
-
-        StoreWakeWordData(mono_data);
-        mn_state = multinet_->detect(multinet_model_data_, const_cast<int16_t*>(mono_data.data()));
     } else {
-        StoreWakeWordData(data);
-        mn_state = multinet_->detect(multinet_model_data_, const_cast<int16_t*>(data.data()));
+        input_buffer_.insert(input_buffer_.end(), data.begin(), data.end());
     }
     
-    if (mn_state == ESP_MN_STATE_DETECTING) {
-        return;
-    } else if (mn_state == ESP_MN_STATE_DETECTED) {
-        esp_mn_results_t *mn_result = multinet_->get_results(multinet_model_data_);
-        for (int i = 0; i < mn_result->num && running_; i++) {
-            ESP_LOGI(TAG, "Custom wake word detected: command_id=%d, string=%s, prob=%f", 
-                    mn_result->command_id[i], mn_result->string, mn_result->prob[i]);
-            auto& command = commands_[mn_result->command_id[i] - 1];
-            if (command.action == "wake") {
-                last_detected_wake_word_ = command.text;
-                running_ = false;
-                
-                if (wake_word_detected_callback_) {
-                    wake_word_detected_callback_(last_detected_wake_word_);
+    int chunksize = multinet_->get_samp_chunksize(multinet_model_data_);
+    while (input_buffer_.size() >= chunksize) {
+        std::vector<int16_t> chunk(input_buffer_.begin(), input_buffer_.begin() + chunksize);
+        StoreWakeWordData(chunk);
+        
+        esp_mn_state_t mn_state = multinet_->detect(multinet_model_data_, chunk.data());
+        
+        if (mn_state == ESP_MN_STATE_DETECTED) {
+            esp_mn_results_t *mn_result = multinet_->get_results(multinet_model_data_);
+            for (int i = 0; i < mn_result->num && running_; i++) {
+                ESP_LOGI(TAG, "Custom wake word detected: command_id=%d, string=%s, prob=%f", 
+                        mn_result->command_id[i], mn_result->string, mn_result->prob[i]);
+                auto& command = commands_[mn_result->command_id[i] - 1];
+                if (command.action == "wake") {
+                    last_detected_wake_word_ = command.text;
+                    running_ = false;
+                    input_buffer_.clear();
+                    
+                    if (wake_word_detected_callback_) {
+                        wake_word_detected_callback_(last_detected_wake_word_);
+                    }
                 }
             }
+            multinet_->clean(multinet_model_data_);
+        } else if (mn_state == ESP_MN_STATE_TIMEOUT) {
+            ESP_LOGD(TAG, "Command word detection timeout, cleaning state");
+            multinet_->clean(multinet_model_data_);
         }
-        multinet_->clean(multinet_model_data_);
-    } else if (mn_state == ESP_MN_STATE_TIMEOUT) {
-        ESP_LOGD(TAG, "Command word detection timeout, cleaning state");
-        multinet_->clean(multinet_model_data_);
+        
+        if (!running_) {
+            break;
+        }
+        input_buffer_.erase(input_buffer_.begin(), input_buffer_.begin() + chunksize);
     }
 }
 
@@ -218,20 +231,56 @@ void CustomWakeWord::EncodeWakeWordData() {
         auto this_ = (CustomWakeWord*)arg;
         {
             auto start_time = esp_timer_get_time();
-            auto encoder = std::make_unique<OpusEncoderWrapper>(16000, 1, OPUS_FRAME_DURATION_MS);
-            encoder->SetComplexity(0); // 0 is the fastest
-
+            // Create encoder
+            esp_opus_enc_config_t opus_enc_cfg = AS_OPUS_ENC_CONFIG();
+            void* encoder_handle = nullptr;
+            auto ret = esp_opus_enc_open(&opus_enc_cfg, sizeof(esp_opus_enc_config_t), &encoder_handle);
+            if (encoder_handle == nullptr) {
+                ESP_LOGE(TAG, "Failed to create audio encoder, error code: %d", ret);
+                std::lock_guard<std::mutex> lock(this_->wake_word_mutex_);
+                this_->wake_word_opus_.push_back(std::vector<uint8_t>());
+                this_->wake_word_cv_.notify_all();
+                return;
+            }
+            // Get frame size
+            int frame_size = 0;
+            int outbuf_size = 0;
+            esp_opus_enc_get_frame_size(encoder_handle, &frame_size, &outbuf_size);
+            frame_size = frame_size / sizeof(int16_t);
+            // Encode all PCM data
             int packets = 0;
+            std::vector<int16_t> in_buffer;
+            esp_audio_enc_in_frame_t in = {};
+            esp_audio_enc_out_frame_t out = {};
             for (auto& pcm: this_->wake_word_pcm_) {
-                encoder->Encode(std::move(pcm), [this_](std::vector<uint8_t>&& opus) {
-                    std::lock_guard<std::mutex> lock(this_->wake_word_mutex_);
-                    this_->wake_word_opus_.emplace_back(std::move(opus));
-                    this_->wake_word_cv_.notify_all();
-                });
-                packets++;
+                if (in_buffer.empty()) {
+                    in_buffer = std::move(pcm);
+                } else {
+                    in_buffer.reserve(in_buffer.size() + pcm.size());
+                    in_buffer.insert(in_buffer.end(), pcm.begin(), pcm.end());
+                }
+                while (in_buffer.size() >= frame_size) {
+                    std::vector<uint8_t> opus_buf(outbuf_size);
+                    in.buffer = (uint8_t *)(in_buffer.data());
+                    in.len = (uint32_t)(frame_size * sizeof(int16_t));
+                    out.buffer = opus_buf.data();
+                    out.len = outbuf_size;
+                    out.encoded_bytes = 0;
+                    ret = esp_opus_enc_process(encoder_handle, &in, &out);
+                    if (ret == ESP_AUDIO_ERR_OK) {
+                        std::lock_guard<std::mutex> lock(this_->wake_word_mutex_);
+                        this_->wake_word_opus_.emplace_back(opus_buf.data(), opus_buf.data() + out.encoded_bytes);
+                        this_->wake_word_cv_.notify_all();
+                        packets++;
+                    } else {
+                        ESP_LOGE(TAG, "Failed to encode audio, error code: %d", ret);
+                    }
+                    in_buffer.erase(in_buffer.begin(), in_buffer.begin() + frame_size);
+                }
             }
             this_->wake_word_pcm_.clear();
-
+            // Close encoder
+            esp_opus_enc_close(encoder_handle);
             auto end_time = esp_timer_get_time();
             ESP_LOGI(TAG, "Encode wake word opus %d packets in %ld ms", packets, (long)((end_time - start_time) / 1000));
 

main/audio/wake_words/custom_wake_word.h

@@ -53,6 +53,8 @@ private:
     AudioCodec* codec_ = nullptr;
     std::string last_detected_wake_word_;
     std::atomic<bool> running_ = false;
+    std::vector<int16_t> input_buffer_;
+    std::mutex input_buffer_mutex_;
 
     TaskHandle_t wake_word_encode_task_ = nullptr;
     StaticTask_t* wake_word_encode_task_buffer_ = nullptr;

main/audio/wake_words/esp_wake_word.cc

@@ -54,21 +54,44 @@ void EspWakeWord::Start() {
 
 void EspWakeWord::Stop() {
     running_ = false;
+
+    std::lock_guard<std::mutex> lock(input_buffer_mutex_);
+    input_buffer_.clear();
 }
 
 void EspWakeWord::Feed(const std::vector<int16_t>& data) {
-    if (wakenet_data_ == nullptr || !running_) {
+    if (wakenet_data_ == nullptr) {
         return;
     }
 
-    int res = wakenet_iface_->detect(wakenet_data_, (int16_t *)data.data());
-    if (res > 0) {
-        last_detected_wake_word_ = wakenet_iface_->get_word_name(wakenet_data_, res);
-        running_ = false;
+    std::lock_guard<std::mutex> lock(input_buffer_mutex_);
+    // Check running state inside lock to avoid TOCTOU race with Stop()
+    if (!running_) {
+        return;
+    }
 
-        if (wake_word_detected_callback_) {
-            wake_word_detected_callback_(last_detected_wake_word_);
+    if (codec_->input_channels() == 2) {
+        for (size_t i = 0; i < data.size(); i += 2) {
+            input_buffer_.push_back(data[i]);
         }
+    } else {
+        input_buffer_.insert(input_buffer_.end(), data.begin(), data.end());
+    }
+
+    int chunksize = wakenet_iface_->get_samp_chunksize(wakenet_data_);
+    while (input_buffer_.size() >= chunksize) {
+        int res = wakenet_iface_->detect(wakenet_data_, input_buffer_.data());
+        if (res > 0) {
+            last_detected_wake_word_ = wakenet_iface_->get_word_name(wakenet_data_, res);
+            running_ = false;
+            input_buffer_.clear();
+
+            if (wake_word_detected_callback_) {
+                wake_word_detected_callback_(last_detected_wake_word_);
+            }
+            break;
+        }
+        input_buffer_.erase(input_buffer_.begin(), input_buffer_.begin() + chunksize);
     }
 }
 

main/audio/wake_words/esp_wake_word.h

@@ -9,6 +9,7 @@
 #include <vector>
 #include <functional>
 #include <atomic>
+#include <mutex>
 
 #include "audio_codec.h"
 #include "wake_word.h"
@@ -37,6 +38,8 @@ private:
 
     std::function<void(const std::string& wake_word)> wake_word_detected_callback_;
     std::string last_detected_wake_word_;
+    std::vector<int16_t> input_buffer_;
+    std::mutex input_buffer_mutex_;
 };
 
 #endif

main/boards/aipi-lite/aipi-lite.cc

@@ -7,7 +7,6 @@
 #include <esp_lcd_panel_vendor.h>
 #include <esp_log.h>
 #include <esp_sleep.h>
-#include <wifi_station.h>
 
 #include "application.h"
 #include "button.h"
@@ -136,9 +135,9 @@ class AIPILite : public WifiBoard {
         boot_button_.OnClick([this]() {
             power_save_timer_->WakeUp();
             auto& app = Application::GetInstance();
-            if (app.GetDeviceState() == kDeviceStateStarting &&
-                !WifiStation::GetInstance().IsConnected()) {
-                ResetWifiConfiguration();
+            if (app.GetDeviceState() == kDeviceStateStarting) {
+                EnterWifiConfigMode();
+                return;
             }
             app.ToggleChatState();
         });
@@ -154,7 +153,7 @@ class AIPILite : public WifiBoard {
             app.SetDeviceState(kDeviceStateWifiConfiguring);
 
             // 重置WiFi配置以确保进入配网模式
-            ResetWifiConfiguration();
+            EnterWifiConfigMode();
         });
 
         power_button_.OnClick([this]() { power_save_timer_->WakeUp(); });
@@ -236,11 +235,11 @@ class AIPILite : public WifiBoard {
         return true;
     }
 
-    virtual void SetPowerSaveMode(bool enabled) override {
-        if (!enabled) {
+    virtual void SetPowerSaveLevel(PowerSaveLevel level) override {
+        if (level != PowerSaveLevel::LOW_POWER) {
             power_save_timer_->WakeUp();
         }
-        WifiBoard::SetPowerSaveMode(enabled);
+        WifiBoard::SetPowerSaveLevel(level);
     }
 };
 

main/boards/atk-dnesp32s3-box/atk_dnesp32s3_box.cc

@@ -8,7 +8,6 @@
 #include "led/single_led.h"
 #include "i2c_device.h"
 
-#include <wifi_station.h>
 #include <esp_log.h>
 #include <driver/i2c_master.h>
 #include <freertos/FreeRTOS.h>
@@ -244,8 +243,9 @@ private:
     void InitializeButtons() {
         boot_button_.OnClick([this]() {
             auto& app = Application::GetInstance();
-            if (app.GetDeviceState() == kDeviceStateStarting && !WifiStation::GetInstance().IsConnected()) {
-                ResetWifiConfiguration();
+            if (app.GetDeviceState() == kDeviceStateStarting) {
+                EnterWifiConfigMode();
+                return;
             }
             app.ToggleChatState();
         });

main/boards/atk-dnesp32s3-box0/atk_dnesp32s3_box0.cc

@@ -13,7 +13,6 @@
 #include "i2c_device.h"
 #include <esp_log.h>
 #include <esp_lcd_panel_vendor.h>
-#include <wifi_station.h>
 
 #include <driver/rtc_io.h>
 #include <esp_sleep.h>
@@ -227,8 +226,9 @@ private:
 
         middle_button_.OnLongPress([this]() {
             auto& app = Application::GetInstance();
-            if (app.GetDeviceState() == kDeviceStateStarting && !WifiStation::GetInstance().IsConnected()) {
-                ResetWifiConfiguration();
+            if (app.GetDeviceState() == kDeviceStateStarting) {
+                EnterWifiConfigMode();
+                return;
             }
 
             if (app.GetDeviceState() != kDeviceStateStarting || app.GetDeviceState() == kDeviceStateWifiConfiguring) {
@@ -377,11 +377,11 @@ public:
         return true;
     }
 
-    virtual void SetPowerSaveMode(bool enabled) override {
-        if (!enabled) {
+    virtual void SetPowerSaveLevel(PowerSaveLevel level) override {
+        if (level != PowerSaveLevel::LOW_POWER) {
             power_save_timer_->WakeUp();
         }
-        WifiBoard::SetPowerSaveMode(enabled);
+        WifiBoard::SetPowerSaveLevel(level);
     }
 };
 

main/boards/atk-dnesp32s3-box2-4g/atk_dnesp32s3_box2.cc

@@ -13,7 +13,6 @@
 #include "i2c_device.h"
 #include <esp_log.h>
 #include <esp_lcd_panel_vendor.h>
-#include <wifi_station.h>
 
 #include <driver/rtc_io.h>
 #include <esp_sleep.h>
@@ -280,9 +279,10 @@ private:
 
             auto& app = Application::GetInstance();
             if (self->GetNetworkType() == NetworkType::WIFI) {
-                if (app.GetDeviceState() == kDeviceStateStarting && !WifiStation::GetInstance().IsConnected()) {
+                if (app.GetDeviceState() == kDeviceStateStarting) {
                     auto& wifi_board = static_cast<WifiBoard&>(self->GetCurrentBoard());
-                    wifi_board.ResetWifiConfiguration();
+                    wifi_board.EnterWifiConfigMode();
+                    return;
                 }
             }
 
@@ -463,11 +463,11 @@ public:
         return true;
     }
 
-    virtual void SetPowerSaveMode(bool enabled) override {
-        if (!enabled) {
+    virtual void SetPowerSaveLevel(PowerSaveLevel level) override {
+        if (level != PowerSaveLevel::LOW_POWER) {
             power_save_timer_->WakeUp();
         }
-        DualNetworkBoard::SetPowerSaveMode(enabled);
+        DualNetworkBoard::SetPowerSaveLevel(level);
     }
 };
 

main/boards/atk-dnesp32s3-box2-wifi/atk_dnesp32s3_box2.cc

@@ -13,7 +13,6 @@
 #include "i2c_device.h"
 #include <esp_log.h>
 #include <esp_lcd_panel_vendor.h>
-#include <wifi_station.h>
 
 #include <driver/rtc_io.h>
 #include <esp_sleep.h>
@@ -262,8 +261,9 @@ private:
             auto self = static_cast<atk_dnesp32s3_box2_wifi*>(usr_data);
 
             auto& app = Application::GetInstance();
-            if (app.GetDeviceState() == kDeviceStateStarting && !WifiStation::GetInstance().IsConnected()) {
-                self->ResetWifiConfiguration();
+            if (app.GetDeviceState() == kDeviceStateStarting) {
+                self->EnterWifiConfigMode();
+                return;
             }
 
             if (self->power_status_ == kDeviceBatterySupply) {
@@ -442,11 +442,11 @@ public:
         return true;
     }
 
-    virtual void SetPowerSaveMode(bool enabled) override {
-        if (!enabled) {
+    virtual void SetPowerSaveLevel(PowerSaveLevel level) override {
+        if (level != PowerSaveLevel::LOW_POWER) {
             power_save_timer_->WakeUp();
         }
-        WifiBoard::SetPowerSaveMode(enabled);
+        WifiBoard::SetPowerSaveLevel(level);
     }
 };
 

main/boards/atk-dnesp32s3/atk_dnesp32s3.cc

@@ -6,13 +6,12 @@
 #include "config.h"
 #include "i2c_device.h"
 #include "led/single_led.h"
-#include "esp32_camera.h"
+#include "esp_video.h"
 
 #include <esp_log.h>
 #include <esp_lcd_panel_vendor.h>
 #include <driver/i2c_master.h>
 #include <driver/spi_common.h>
-#include <wifi_station.h>
 
 #define TAG "atk_dnesp32s3"
 
@@ -50,7 +49,7 @@ private:
     Button boot_button_;
     LcdDisplay* display_;
     XL9555* xl9555_;
-    Esp32Camera* camera_;
+    EspVideo* camera_;
 
     void InitializeI2c() {
         // Initialize I2C peripheral
@@ -87,8 +86,9 @@ private:
     void InitializeButtons() {
         boot_button_.OnClick([this]() {
             auto& app = Application::GetInstance();
-            if (app.GetDeviceState() == kDeviceStateStarting && !WifiStation::GetInstance().IsConnected()) {
-                ResetWifiConfiguration();
+            if (app.GetDeviceState() == kDeviceStateStarting) {
+                EnterWifiConfigMode();
+                return;
             }
             app.ToggleChatState();
         });
@@ -179,7 +179,7 @@ private:
             .dvp = &dvp_config,
         };
 
-        camera_ = new Esp32Camera(video_config);
+        camera_ = new EspVideo(video_config);
     }
 
 public:

main/boards/atk-dnesp32s3m-wifi/atk_dnesp32s3m.cc

@@ -9,7 +9,6 @@
 #include "driver/gpio.h"
 #include "assets/lang_config.h"
 
-#include <wifi_station.h>
 #include <esp_log.h>
 #include <driver/i2c_master.h>
 #include <esp_lcd_panel_vendor.h>
@@ -60,8 +59,9 @@ private:
     void InitializeButtons() {
         boot_button_.OnClick([this]() {
             auto& app = Application::GetInstance();
-            if (app.GetDeviceState() == kDeviceStateStarting && !WifiStation::GetInstance().IsConnected()) {
-                ResetWifiConfiguration();
+            if (app.GetDeviceState() == kDeviceStateStarting) {
+                EnterWifiConfigMode();
+                return;
             }
             app.ToggleChatState();
         });

main/boards/atom-echos3r/atom_echos3r.cc

@@ -8,7 +8,6 @@
 
 #include <esp_log.h>
 #include <driver/i2c_master.h>
-#include <wifi_station.h>
 
 #define TAG "AtomEchoS3R"
 
@@ -57,8 +56,9 @@ private:
     void InitializeButtons() {
         boot_button_.OnClick([this]() {
             auto& app = Application::GetInstance();
-            if (app.GetDeviceState() == kDeviceStateStarting && !WifiStation::GetInstance().IsConnected()) {
-                ResetWifiConfiguration();
+            if (app.GetDeviceState() == kDeviceStateStarting) {
+                EnterWifiConfigMode();
+                return;
             }
             app.ToggleChatState();
         });

main/boards/atommatrix-echo-base/atommatrix_echo_base.cc

@@ -7,7 +7,6 @@
 
 #include <esp_log.h>
 #include <driver/i2c_master.h>
-#include <wifi_station.h>
 #include "led/circular_strip.h"
 
 #define TAG "XX+EchoBase"
@@ -91,8 +90,9 @@ private:
 
             ESP_LOGI(TAG, "  ===>>>  face_button_.OnClick ");
             auto& app = Application::GetInstance();
-            if (app.GetDeviceState() == kDeviceStateStarting && !WifiStation::GetInstance().IsConnected()) {
-                ResetWifiConfiguration();
+            if (app.GetDeviceState() == kDeviceStateStarting) {
+                EnterWifiConfigMode();
+                return;
             } 
             app.ToggleChatState();
         });

main/boards/atoms3-echo-base/atoms3_echo_base.cc

@@ -9,7 +9,6 @@
 
 #include <esp_log.h>
 #include <driver/i2c_master.h>
-#include <wifi_station.h>
 #include <esp_lcd_panel_io.h>
 #include <esp_lcd_panel_ops.h>
 #include <esp_lcd_gc9a01.h>
@@ -180,8 +179,9 @@ private:
     void InitializeButtons() {
         boot_button_.OnClick([this]() {
             auto& app = Application::GetInstance();
-            if (app.GetDeviceState() == kDeviceStateStarting && !WifiStation::GetInstance().IsConnected()) {
-                ResetWifiConfiguration();
+            if (app.GetDeviceState() == kDeviceStateStarting) {
+                EnterWifiConfigMode();
+                return;
             }
             app.ToggleChatState();
         });

main/boards/atoms3r-cam-m12-echo-base/README.md

@@ -14,12 +14,6 @@ AtomS3R CAM、AtomS3R M12 是 M5Stack 推出的基于 ESP32-S3-PICO-1-N8R8 的
 
 两款开发版均**不带屏幕、不带额外按键**，需要使用语音唤醒。必要时，需要使用 `idf.py monitor` 查看 log 以确定运行状态。
 
-> ![NOTE]
->
-> 自版本 [待定] 起，由于依赖库不支持 OV3660 传感器，AtomS3R M12 无法使用摄像头识别功能。
->
-> AtomS3R CAM 不受影响；使用旧版本小智固件的 AtomS3R M12 不受影响。
-
 ## 配置、编译命令
 
 **配置编译目标为 ESP32S3**

main/boards/atoms3r-cam-m12-echo-base/atoms3r_cam_m12_echo_base.cc

@@ -8,7 +8,6 @@
 
 #include <esp_log.h>
 #include <driver/i2c_master.h>
-#include <wifi_station.h>
 #include "esp32_camera.h"
 
 #define TAG "AtomS3R CAM/M12 + EchoBase"
@@ -127,47 +126,33 @@ private:
     }
 
     void InitializeCamera() {
-        static esp_cam_ctlr_dvp_pin_config_t dvp_pin_config = {
-            .data_width = CAM_CTLR_DATA_WIDTH_8,
-            .data_io = {
-                [0] = CAMERA_PIN_D0,
-                [1] = CAMERA_PIN_D1,
-                [2] = CAMERA_PIN_D2,
-                [3] = CAMERA_PIN_D3,
-                [4] = CAMERA_PIN_D4,
-                [5] = CAMERA_PIN_D5,
-                [6] = CAMERA_PIN_D6,
-                [7] = CAMERA_PIN_D7,
-            },
-            .vsync_io = CAMERA_PIN_VSYNC,
-            .de_io = CAMERA_PIN_HREF,
-            .pclk_io = CAMERA_PIN_PCLK,
-            .xclk_io = CAMERA_PIN_XCLK,
-        };
+        camera_config_t config = {};
+        config.pin_d0 = CAMERA_PIN_D0;
+        config.pin_d1 = CAMERA_PIN_D1;
+        config.pin_d2 = CAMERA_PIN_D2;
+        config.pin_d3 = CAMERA_PIN_D3;
+        config.pin_d4 = CAMERA_PIN_D4;
+        config.pin_d5 = CAMERA_PIN_D5;
+        config.pin_d6 = CAMERA_PIN_D6;
+        config.pin_d7 = CAMERA_PIN_D7;
+        config.pin_xclk = CAMERA_PIN_XCLK;
+        config.pin_pclk = CAMERA_PIN_PCLK;
+        config.pin_vsync = CAMERA_PIN_VSYNC;
+        config.pin_href = CAMERA_PIN_HREF;
+        config.pin_sccb_sda = CAMERA_PIN_SIOD;
+        config.pin_sccb_scl = CAMERA_PIN_SIOC;
+        config.sccb_i2c_port = 1;
+        config.pin_pwdn = CAMERA_PIN_PWDN;
+        config.pin_reset = CAMERA_PIN_RESET;
+        config.xclk_freq_hz = XCLK_FREQ_HZ;
+        config.pixel_format = PIXFORMAT_RGB565;
+        config.frame_size = FRAMESIZE_QVGA;
+        config.jpeg_quality = 12;
+        config.fb_count = 1;
+        config.fb_location = CAMERA_FB_IN_PSRAM;
+        config.grab_mode = CAMERA_GRAB_WHEN_EMPTY;
 
-        esp_video_init_sccb_config_t sccb_config = {
-            .init_sccb = true,
-            .i2c_config = {
-                .port = 1,
-                .scl_pin = CAMERA_PIN_SIOC,
-                .sda_pin = CAMERA_PIN_SIOD,
-            },
-            .freq = 100000,
-        };
-
-        esp_video_init_dvp_config_t dvp_config = {
-            .sccb_config = sccb_config,
-            .reset_pin = CAMERA_PIN_RESET,
-            .pwdn_pin = CAMERA_PIN_PWDN,
-            .dvp_pin = dvp_pin_config,
-            .xclk_freq = XCLK_FREQ_HZ,
-        };
-
-        esp_video_init_config_t video_config = {
-            .dvp = &dvp_config,
-        };
-
-        camera_ = new Esp32Camera(video_config);
+        camera_ = new Esp32Camera(config);
         camera_->SetHMirror(false);
     }
 

main/boards/atoms3r-cam-m12-echo-base/config.json

@@ -5,10 +5,7 @@
             "name": "atoms3r-cam-m12-echo-base",
             "sdkconfig_append": [
                 "CONFIG_ESPTOOLPY_FLASHSIZE_8MB=y",
-                "CONFIG_PARTITION_TABLE_CUSTOM_FILENAME=\"partitions/v2/8m.csv\"",
-                "CONFIG_CAMERA_GC0308=y",
-                "CONFIG_CAMERA_GC0308_AUTO_DETECT_DVP_INTERFACE_SENSOR=y",
-                "CONFIG_CAMERA_GC0308_DVP_YUV422_320X240_20FPS=y"
+                "CONFIG_PARTITION_TABLE_CUSTOM_FILENAME=\"partitions/v2/8m.csv\""
             ]
         }
     ]

main/boards/atoms3r-echo-base/atoms3r_echo_base.cc

@@ -9,7 +9,6 @@
 
 #include <esp_log.h>
 #include <driver/i2c_master.h>
-#include <wifi_station.h>
 #include <esp_lcd_panel_io.h>
 #include <esp_lcd_panel_ops.h>
 #include <esp_lcd_gc9a01.h>
@@ -258,8 +257,9 @@ private:
     void InitializeButtons() {
         boot_button_.OnClick([this]() {
             auto& app = Application::GetInstance();
-            if (app.GetDeviceState() == kDeviceStateStarting && !WifiStation::GetInstance().IsConnected()) {
-                ResetWifiConfiguration();
+            if (app.GetDeviceState() == kDeviceStateStarting) {
+                EnterWifiConfigMode();
+                return;
             }
             app.ToggleChatState();
         });

main/boards/bread-compact-esp32-lcd/esp32_bread_board_lcd.cc

@@ -1,4 +1,4 @@
-#include "dual_network_board.h"
+#include "wifi_board.h"
 #include "codecs/no_audio_codec.h"
 #include "display/lcd_display.h"
 #include "system_reset.h"
@@ -7,7 +7,6 @@
 #include "config.h"
 #include "led/single_led.h"
 
-#include <wifi_station.h>
 #include <esp_log.h>
 #include <driver/i2c_master.h>
 #include <esp_lcd_panel_vendor.h>
@@ -58,7 +57,7 @@ static const gc9a01_lcd_init_cmd_t gc9107_lcd_init_cmds[] = {
  
 #define TAG "ESP32-LCD-MarsbearSupport"
 
-class CompactWifiBoardLCD : public DualNetworkBoard {
+class CompactWifiBoardLCD : public WifiBoard {
 private:
     Button boot_button_;
     Button touch_button_;
@@ -137,25 +136,14 @@ private:
 
         boot_button_.OnClick([this]() {
             auto& app = Application::GetInstance();
-            if (GetNetworkType() == NetworkType::WIFI) {
-                if (app.GetDeviceState() == kDeviceStateStarting && !WifiStation::GetInstance().IsConnected()) {
-                    // cast to WifiBoard
-                    auto& wifi_board = static_cast<WifiBoard&>(GetCurrentBoard());
-                    wifi_board.ResetWifiConfiguration();
-                }
+            if (app.GetDeviceState() == kDeviceStateStarting) {
+                EnterWifiConfigMode();
+                return;
             }
             gpio_set_level(BUILTIN_LED_GPIO, 1);
             app.ToggleChatState();
         });
 
-
-        boot_button_.OnDoubleClick([this]() {
-            auto& app = Application::GetInstance();
-            if (app.GetDeviceState() == kDeviceStateStarting || app.GetDeviceState() == kDeviceStateWifiConfiguring) {
-                SwitchNetworkType();
-            }
-        });
-
         asr_button_.OnClick([this]() {
             std::string wake_word="你好小智";
             Application::GetInstance().WakeWordInvoke(wake_word);
@@ -174,8 +162,7 @@ private:
     }
 
 public:
-    CompactWifiBoardLCD() :
-        DualNetworkBoard(ML307_TX_PIN, ML307_RX_PIN),
+    CompactWifiBoardLCD() : WifiBoard(),
         boot_button_(BOOT_BUTTON_GPIO), touch_button_(TOUCH_BUTTON_GPIO), asr_button_(ASR_BUTTON_GPIO) {
         InitializeSpi();
         InitializeLcdDisplay();

main/boards/bread-compact-esp32/config.h

@@ -45,7 +45,7 @@
 #elif CONFIG_OLED_SSD1306_128X64
 #define DISPLAY_HEIGHT  64
 #else
-#error "未选择 OLED 屏幕类型"
+#error "OLED display type is not selected"
 #endif
 
 #define DISPLAY_MIRROR_X true

main/boards/bread-compact-esp32/esp32_bread_board.cc

@@ -1,4 +1,4 @@
-#include "dual_network_board.h"
+#include "wifi_board.h"
 #include "codecs/no_audio_codec.h"
 #include "system_reset.h"
 #include "application.h"
@@ -9,7 +9,6 @@
 #include "led/single_led.h"
 #include "display/oled_display.h"
 
-#include <wifi_station.h>
 #include <esp_log.h>
 #include <driver/i2c_master.h>
 #include <esp_lcd_panel_ops.h>
@@ -17,7 +16,7 @@
 
 #define TAG "ESP32-MarsbearSupport"
 
-class CompactWifiBoard : public DualNetworkBoard {
+class CompactWifiBoard : public WifiBoard {
 private:
     Button boot_button_;
     Button touch_button_;
@@ -105,25 +104,14 @@ private:
 
         boot_button_.OnClick([this]() {
             auto& app = Application::GetInstance();
-            if (GetNetworkType() == NetworkType::WIFI) {
-                if (app.GetDeviceState() == kDeviceStateStarting && !WifiStation::GetInstance().IsConnected()) {
-                    // cast to WifiBoard
-                    auto& wifi_board = static_cast<WifiBoard&>(GetCurrentBoard());
-                    wifi_board.ResetWifiConfiguration();
-                }
+            if (app.GetDeviceState() == kDeviceStateStarting) {
+                EnterWifiConfigMode();
+                return;
             }
             gpio_set_level(BUILTIN_LED_GPIO, 1);
             app.ToggleChatState();
         });
 
-
-        boot_button_.OnDoubleClick([this]() {
-            auto& app = Application::GetInstance();
-            if (app.GetDeviceState() == kDeviceStateStarting || app.GetDeviceState() == kDeviceStateWifiConfiguring) {
-                SwitchNetworkType();
-            }
-        });
-
         asr_button_.OnClick([this]() {
             std::string wake_word="你好小智";
             Application::GetInstance().WakeWordInvoke(wake_word);
@@ -145,7 +133,7 @@ private:
     }
 
 public:
-    CompactWifiBoard() : DualNetworkBoard(ML307_TX_PIN, ML307_RX_PIN), boot_button_(BOOT_BUTTON_GPIO), touch_button_(TOUCH_BUTTON_GPIO), asr_button_(ASR_BUTTON_GPIO)
+    CompactWifiBoard() : WifiBoard(), boot_button_(BOOT_BUTTON_GPIO), touch_button_(TOUCH_BUTTON_GPIO), asr_button_(ASR_BUTTON_GPIO)
     {
         InitializeDisplayI2c();
         InitializeSsd1306Display();

main/boards/bread-compact-ml307/compact_ml307_board.cc

@@ -14,7 +14,6 @@
 #include <driver/i2c_master.h>
 #include <esp_lcd_panel_ops.h>
 #include <esp_lcd_panel_vendor.h>
-#include <wifi_station.h>
 
 #define TAG "CompactMl307Board"
 
@@ -96,10 +95,11 @@ private:
         boot_button_.OnClick([this]() {
             auto& app = Application::GetInstance();
             if (GetNetworkType() == NetworkType::WIFI) {
-                if (app.GetDeviceState() == kDeviceStateStarting && !WifiStation::GetInstance().IsConnected()) {
+                if (app.GetDeviceState() == kDeviceStateStarting) {
                     // cast to WifiBoard
                     auto& wifi_board = static_cast<WifiBoard&>(GetCurrentBoard());
-                    wifi_board.ResetWifiConfiguration();
+                    wifi_board.EnterWifiConfigMode();
+                    return;
                 }
             }
             app.ToggleChatState();