Delay init success sound playback and remove gif playback delay (#1748)

* refactor: Remove hardcoded loop delay for GIF playback in LcdDisplay class * chore: Update esp-ml307 and uart-eth-modem component versions in idf_component.yml - Bump esp-ml307 version from ~3.6.3 to ~3.6.4 - Update uart-eth-modem version from ~0.3.1 to ~0.3.2 * feat: Add PrintPmLocks method to SystemInfo class - Introduced PrintPmLocks method to display power management locks using esp_pm_dump_locks. - Updated system_info.h to declare the new method. * refactor: Streamline audio codec initialization and enablement - Removed redundant channel enable checks from AudioCodec::Start. - Added channel enablement in CreateDuplexChannels for various audio codecs. - Implemented EnableInput and EnableOutput methods in NoAudioCodec for better control over input/output states. * refactor: Delay audio success sound playback until after activation completion - Moved the success sound playback to a scheduled task to ensure it occurs after the activation process is complete. - This change improves the responsiveness of the application during activation events. * refactor: Update camera integration from EspVideo to Esp32Camera - Replaced EspVideo with Esp32Camera for improved camera configuration and initialization. - Streamlined camera setup by utilizing a new configuration structure for better clarity and maintainability. - Updated README.md to remove outdated camera sensor configuration instructions. * refactor: Update audio demuxing process in AudioService - Replaced the existing demuxer instance with a local unique pointer in the PlaySound method for better memory management. - Moved the OnDemuxerFinished callback setup into the PlaySound method to ensure it is correctly associated with the new demuxer instance. - Removed the member variable demuxer_ from AudioService to streamline the class structure.
2026-02-11 06:33:48 +00:00 · 2026-02-08 22:09:45 +08:00
parent 7b7d22c495
commit 9215a04a7e
25 changed files with 105 additions and 94 deletions
--- a/main/application.cc
+++ b/main/application.cc
@@ -309,13 +309,15 @@ void Application::HandleActivationDoneEvent() {
    display->ShowNotification(message.c_str());
    display->SetChatMessage("system", "");

-    // Play the success sound to indicate the device is ready
-    audio_service_.PlaySound(Lang::Sounds::OGG_SUCCESS);
-
    // Release OTA object after activation is complete
    ota_.reset();
    auto& board = Board::GetInstance();
    board.SetPowerSaveLevel(PowerSaveLevel::LOW_POWER);
+
+    Schedule([this]() {
+        // Play the success sound to indicate the device is ready
+        audio_service_.PlaySound(Lang::Sounds::OGG_SUCCESS);
+    });
 }

 void Application::ActivationTask() {
--- a/main/audio/audio_codec.cc
+++ b/main/audio/audio_codec.cc
@@ -34,16 +34,6 @@ void AudioCodec::Start() {
        output_volume_ = 10;
    }

-    if (tx_handle_ != nullptr) {
-        ESP_ERROR_CHECK(i2s_channel_enable(tx_handle_));
-    }
-
-    if (rx_handle_ != nullptr) {
-        ESP_ERROR_CHECK(i2s_channel_enable(rx_handle_));
-    }
-
-    EnableInput(true);
-    EnableOutput(true);
    ESP_LOGI(TAG, "Audio codec started");
 }

--- a/main/audio/audio_service.cc
+++ b/main/audio/audio_service.cc
@@ -39,15 +39,6 @@

 AudioService::AudioService() {
    event_group_ = xEventGroupCreate();
-
-    demuxer_.OnDemuxerFinished([this](const uint8_t* data, int sample_rate, size_t size){
-        auto packet = std::make_unique<AudioStreamPacket>();
-        packet->sample_rate = sample_rate;
-        packet->frame_duration = 60;
-        packet->payload.resize(size);
-        std::memcpy(packet->payload.data(), data, size);
-        PushPacketToDecodeQueue(std::move(packet), true);
-    });
 }

 AudioService::~AudioService() {
@@ -314,6 +305,7 @@ void AudioService::AudioOutputTask() {
            esp_timer_start_periodic(audio_power_timer_, AUDIO_POWER_CHECK_INTERVAL_MS * 1000);
            codec_->EnableOutput(true);
        }
+
        codec_->OutputData(task->pcm);

        /* Update the last output time */
@@ -647,8 +639,18 @@ void AudioService::PlaySound(const std::string_view& ogg) {

    const auto* buf = reinterpret_cast<const uint8_t*>(ogg.data());
    size_t size = ogg.size();
-    demuxer_.Reset();
-    demuxer_.Process(buf, size);
+
+    auto demuxer = std::make_unique<OggDemuxer>();
+    demuxer->OnDemuxerFinished([this](const uint8_t* data, int sample_rate, size_t size){
+        auto packet = std::make_unique<AudioStreamPacket>();
+        packet->sample_rate = sample_rate;
+        packet->frame_duration = 60;
+        packet->payload.resize(size);
+        std::memcpy(packet->payload.data(), data, size);
+        PushPacketToDecodeQueue(std::move(packet), true);
+    });
+    demuxer->Reset();
+    demuxer->Process(buf, size);
 }

 bool AudioService::IsIdle() {
--- a/main/audio/audio_service.h
+++ b/main/audio/audio_service.h
@@ -146,8 +146,6 @@ private:
    std::mutex input_resampler_mutex_;
    esp_ae_rate_cvt_handle_t input_resampler_ = nullptr;
    esp_ae_rate_cvt_handle_t output_resampler_ = nullptr;
-
-    OggDemuxer      demuxer_;
    
    // Encoder/Decoder state
    int encoder_sample_rate_ = 16000;
--- a/main/audio/codecs/box_audio_codec.cc
+++ b/main/audio/codecs/box_audio_codec.cc
@@ -176,6 +176,8 @@ void BoxAudioCodec::CreateDuplexChannels(gpio_num_t mclk, gpio_num_t bclk, gpio_

    ESP_ERROR_CHECK(i2s_channel_init_std_mode(tx_handle_, &std_cfg));
    ESP_ERROR_CHECK(i2s_channel_init_tdm_mode(rx_handle_, &tdm_cfg));
+    ESP_ERROR_CHECK(i2s_channel_enable(tx_handle_));
+    ESP_ERROR_CHECK(i2s_channel_enable(rx_handle_));
    ESP_LOGI(TAG, "Duplex channels created");
 }

--- a/main/audio/codecs/es8311_audio_codec.cc
+++ b/main/audio/codecs/es8311_audio_codec.cc
@@ -150,6 +150,8 @@ void Es8311AudioCodec::CreateDuplexChannels(gpio_num_t mclk, gpio_num_t bclk, gp

    ESP_ERROR_CHECK(i2s_channel_init_std_mode(tx_handle_, &std_cfg));
    ESP_ERROR_CHECK(i2s_channel_init_std_mode(rx_handle_, &std_cfg));
+    ESP_ERROR_CHECK(i2s_channel_enable(tx_handle_));
+    ESP_ERROR_CHECK(i2s_channel_enable(rx_handle_));
    ESP_LOGI(TAG, "Duplex channels created");
 }

--- a/main/audio/codecs/es8374_audio_codec.cc
+++ b/main/audio/codecs/es8374_audio_codec.cc
@@ -126,6 +126,8 @@ void Es8374AudioCodec::CreateDuplexChannels(gpio_num_t mclk, gpio_num_t bclk, gp

    ESP_ERROR_CHECK(i2s_channel_init_std_mode(tx_handle_, &std_cfg));
    ESP_ERROR_CHECK(i2s_channel_init_std_mode(rx_handle_, &std_cfg));
+    ESP_ERROR_CHECK(i2s_channel_enable(tx_handle_));
+    ESP_ERROR_CHECK(i2s_channel_enable(rx_handle_));
    ESP_LOGI(TAG, "Duplex channels created");
 }

--- a/main/audio/codecs/es8388_audio_codec.cc
+++ b/main/audio/codecs/es8388_audio_codec.cc
@@ -131,6 +131,8 @@ void Es8388AudioCodec::CreateDuplexChannels(gpio_num_t mclk, gpio_num_t bclk, gp

    ESP_ERROR_CHECK(i2s_channel_init_std_mode(tx_handle_, &std_cfg));
    ESP_ERROR_CHECK(i2s_channel_init_std_mode(rx_handle_, &std_cfg));
+    ESP_ERROR_CHECK(i2s_channel_enable(tx_handle_));
+    ESP_ERROR_CHECK(i2s_channel_enable(rx_handle_));
    ESP_LOGI(TAG, "Duplex channels created");
 }

--- a/main/audio/codecs/es8389_audio_codec.cc
+++ b/main/audio/codecs/es8389_audio_codec.cc
@@ -132,6 +132,8 @@ void Es8389AudioCodec::CreateDuplexChannels(gpio_num_t mclk, gpio_num_t bclk, gp

    ESP_ERROR_CHECK(i2s_channel_init_std_mode(tx_handle_, &std_cfg));
    ESP_ERROR_CHECK(i2s_channel_init_std_mode(rx_handle_, &std_cfg));
+    ESP_ERROR_CHECK(i2s_channel_enable(tx_handle_));
+    ESP_ERROR_CHECK(i2s_channel_enable(rx_handle_));
    ESP_LOGI(TAG, "Duplex channels created");
 }

--- a/main/audio/codecs/no_audio_codec.cc
+++ b/main/audio/codecs/no_audio_codec.cc
@@ -254,6 +254,32 @@ int NoAudioCodec::Read(int16_t* dest, int samples) {
    return samples;
 }

+void NoAudioCodec::EnableInput(bool enable) {
+    std::lock_guard<std::mutex> lock(data_if_mutex_);
+    if (enable == input_enabled_) {
+        return;
+    }
+    if (enable) {
+        ESP_ERROR_CHECK(i2s_channel_enable(rx_handle_));
+    } else {
+        ESP_ERROR_CHECK(i2s_channel_disable(rx_handle_));
+    }
+    AudioCodec::EnableInput(enable);
+}
+
+void NoAudioCodec::EnableOutput(bool enable) {
+    std::lock_guard<std::mutex> lock(data_if_mutex_);
+    if (enable == output_enabled_) {
+        return;
+    }
+    if (enable) {
+        ESP_ERROR_CHECK(i2s_channel_enable(tx_handle_));
+    } else {
+        ESP_ERROR_CHECK(i2s_channel_disable(tx_handle_));
+    }
+    AudioCodec::EnableOutput(enable);
+}
+
 // Delegating constructor: calls the main constructor with default slot mask
 NoAudioCodecSimplexPdm::NoAudioCodecSimplexPdm(int input_sample_rate, int output_sample_rate, gpio_num_t spk_bclk, gpio_num_t spk_ws, gpio_num_t spk_dout, gpio_num_t mic_sck, gpio_num_t mic_din) 
    : NoAudioCodecSimplexPdm(input_sample_rate, output_sample_rate, spk_bclk, spk_ws, spk_dout, I2S_STD_SLOT_LEFT, mic_sck, mic_din) {
--- a/main/audio/codecs/no_audio_codec.h
+++ b/main/audio/codecs/no_audio_codec.h
@@ -13,6 +13,8 @@ protected:

    virtual int Write(const int16_t* data, int samples) override;
    virtual int Read(int16_t* dest, int samples) override;
+    virtual void EnableInput(bool enable) override;
+    virtual void EnableOutput(bool enable) override;

 public:
    virtual ~NoAudioCodec();
--- a/main/boards/bread-compact-wifi-s3cam/README.md
+++ b/main/boards/bread-compact-wifi-s3cam/README.md
@@ -24,26 +24,6 @@ idf.py menuconfig
 Xiaozhi Assistant -> Board Type ->面包板新版接线（WiFi）+ LCD + Camera
 ```

-**配置摄像头传感器：**
-
-> **注意：** 确认摄像头传感器型号，确定型号在 esp_cam_sensor 支持的范围内。当前板子用的是 OV2640，是符合支持范围。
-
-在 menuconfig 中按以下步骤启用对应型号的支持：
-
-1. **导航到传感器配置：**
-   ```
-   (Top) → Component config → Espressif Camera Sensors Configurations → Camera Sensor Configuration → Select and Set Camera Sensor
-   ```
-
-2. **选择传感器型号：**
-   - 选中所需的传感器型号（OV2640）
-
-3. **配置传感器参数：**
-   - 按 → 进入传感器详细设置
-   - 启用 **Auto detect**
-   - 推荐将 **default output format** 调整为 **YUV422** 及合适的分辨率大小
-   - （目前支持 YUV422、RGB565，YUV422 更节省内存空间）
-
 **编译烧入：**

 ```bash
--- a/main/boards/bread-compact-wifi-s3cam/compact_wifi_board_s3cam.cc
+++ b/main/boards/bread-compact-wifi-s3cam/compact_wifi_board_s3cam.cc
@@ -8,7 +8,7 @@
 #include "mcp_server.h"
 #include "lamp_controller.h"
 #include "led/single_led.h"
-#include "esp_video.h"
+#include "esp32_camera.h"

 #include <esp_log.h>
 #include <driver/i2c_master.h>
@@ -65,7 +65,7 @@ private:
 
    Button boot_button_;
    LcdDisplay* display_;
-     EspVideo* camera_;
+    Esp32Camera* camera_;

    void InitializeSpi() {
        spi_bus_config_t buscfg = {};
@@ -125,47 +125,32 @@ 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,
-        };
-
-        esp_video_init_sccb_config_t sccb_config = {
-            .init_sccb = true,
-            .i2c_config = {
-                .port = 0,
-                .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 EspVideo(video_config);
+        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 = 0;
+        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_VGA;
+        config.jpeg_quality = 12;
+        config.fb_count = 1;
+        config.fb_location = CAMERA_FB_IN_PSRAM;
+        config.grab_mode = CAMERA_GRAB_WHEN_EMPTY;
+        camera_ = new Esp32Camera(config);
        camera_->SetHMirror(false);
    }

--- a/main/boards/df-k10/k10_audio_codec.cc
+++ b/main/boards/df-k10/k10_audio_codec.cc
@@ -152,6 +152,8 @@ void K10AudioCodec::CreateDuplexChannels(gpio_num_t mclk, gpio_num_t bclk, gpio_

    ESP_ERROR_CHECK(i2s_channel_init_std_mode(tx_handle_, &std_cfg));
    ESP_ERROR_CHECK(i2s_channel_init_tdm_mode(rx_handle_, &tdm_cfg));
+    ESP_ERROR_CHECK(i2s_channel_enable(tx_handle_));
+    ESP_ERROR_CHECK(i2s_channel_enable(rx_handle_));
    ESP_LOGI(TAG, "Duplex channels created");
 }

--- a/main/boards/esp-box-lite/box_audio_codec_lite.cc
+++ b/main/boards/esp-box-lite/box_audio_codec_lite.cc
@@ -165,6 +165,8 @@ void BoxAudioCodecLite::CreateDuplexChannels(gpio_num_t mclk, gpio_num_t bclk, g

    ESP_ERROR_CHECK(i2s_channel_init_std_mode(tx_handle_, &std_cfg));
    ESP_ERROR_CHECK(i2s_channel_init_tdm_mode(rx_handle_, &tdm_cfg));
+    ESP_ERROR_CHECK(i2s_channel_enable(tx_handle_));
+    ESP_ERROR_CHECK(i2s_channel_enable(rx_handle_));
    ESP_LOGI(TAG, "Duplex channels created");
 }

--- a/main/boards/esp-hi/adc_pdm_audio_codec.cc
+++ b/main/boards/esp-hi/adc_pdm_audio_codec.cc
@@ -81,6 +81,7 @@ AdcPdmAudioCodec::AdcPdmAudioCodec(int input_sample_rate, int output_sample_rate
    const i2s_pdm_tx_config_t *p_i2s_cfg = &pdm_cfg_default;

    ESP_ERROR_CHECK(i2s_channel_init_pdm_tx_mode(tx_handle_, p_i2s_cfg));
+    ESP_ERROR_CHECK(i2s_channel_enable(tx_handle_));

    audio_codec_i2s_cfg_t i2s_cfg = {
        .port = I2S_NUM_0,
--- a/main/boards/esp-sensairshuttle/adc_pdm_audio_codec.cc
+++ b/main/boards/esp-sensairshuttle/adc_pdm_audio_codec.cc
@@ -81,6 +81,7 @@ AdcPdmAudioCodec::AdcPdmAudioCodec(int input_sample_rate, int output_sample_rate
    const i2s_pdm_tx_config_t *p_i2s_cfg = &pdm_cfg_default;

    ESP_ERROR_CHECK(i2s_channel_init_pdm_tx_mode(tx_handle_, p_i2s_cfg));
+    ESP_ERROR_CHECK(i2s_channel_enable(tx_handle_));

    audio_codec_i2s_cfg_t i2s_cfg = {
        .port = I2S_NUM_0,
--- a/main/boards/lichuang-dev/lichuang_dev_board.cc
+++ b/main/boards/lichuang-dev/lichuang_dev_board.cc
@@ -230,7 +230,7 @@ private:
        config.pin_reset = CAMERA_PIN_RESET;
        config.xclk_freq_hz = XCLK_FREQ_HZ;
        config.pixel_format = PIXFORMAT_RGB565;
-        config.frame_size = FRAMESIZE_VGA;
+        config.frame_size = FRAMESIZE_QVGA;
        config.jpeg_quality = 12;
        config.fb_count = 1;
        config.fb_location = CAMERA_FB_IN_PSRAM;
--- a/main/boards/m5stack-core-s3/cores3_audio_codec.cc
+++ b/main/boards/m5stack-core-s3/cores3_audio_codec.cc
@@ -177,6 +177,8 @@ void CoreS3AudioCodec::CreateDuplexChannels(gpio_num_t mclk, gpio_num_t bclk, gp

    ESP_ERROR_CHECK(i2s_channel_init_std_mode(tx_handle_, &std_cfg));
    ESP_ERROR_CHECK(i2s_channel_init_tdm_mode(rx_handle_, &tdm_cfg));
+    ESP_ERROR_CHECK(i2s_channel_enable(tx_handle_));
+    ESP_ERROR_CHECK(i2s_channel_enable(rx_handle_));
    ESP_LOGI(TAG, "Duplex channels created");
 }

--- a/main/boards/m5stack-tab5/tab5_audio_codec.cc
+++ b/main/boards/m5stack-tab5/tab5_audio_codec.cc
@@ -176,6 +176,8 @@ void Tab5AudioCodec::CreateDuplexChannels(gpio_num_t mclk, gpio_num_t bclk, gpio

    ESP_ERROR_CHECK(i2s_channel_init_std_mode(tx_handle_, &std_cfg));
    ESP_ERROR_CHECK(i2s_channel_init_tdm_mode(rx_handle_, &tdm_cfg));
+    ESP_ERROR_CHECK(i2s_channel_enable(tx_handle_));
+    ESP_ERROR_CHECK(i2s_channel_enable(rx_handle_));
    ESP_LOGI(TAG, "Duplex channels created");
 }

--- a/main/boards/sensecap-watcher/sensecap_audio_codec.cc
+++ b/main/boards/sensecap-watcher/sensecap_audio_codec.cc
@@ -143,6 +143,8 @@ void SensecapAudioCodec::CreateDuplexChannels(gpio_num_t mclk, gpio_num_t bclk,

    std_cfg.slot_cfg.slot_mask = I2S_STD_SLOT_RIGHT;
    ESP_ERROR_CHECK(i2s_channel_init_std_mode(rx_handle_, &std_cfg));
+    ESP_ERROR_CHECK(i2s_channel_enable(tx_handle_));
+    ESP_ERROR_CHECK(i2s_channel_enable(rx_handle_));
    ESP_LOGI(TAG, "Duplex channels created");
 }

--- a/main/display/lcd_display.cc
+++ b/main/display/lcd_display.cc
@@ -1032,8 +1032,6 @@ void LcdDisplay::SetEmotion(const char* emotion) {
        gif_controller_ = std::make_unique<LvglGif>(image->image_dsc());
        
        if (gif_controller_->IsLoaded()) {
-            // Set loop delay to 1000ms
-            gif_controller_->SetLoopDelay(3000);
            // Set up frame update callback
            gif_controller_->SetFrameCallback([this]() {
                lv_image_set_src(emoji_image_, gif_controller_->image_dsc());
--- a/main/idf_component.yml
+++ b/main/idf_component.yml
@@ -22,9 +22,9 @@ dependencies:
  78/esp-wifi-connect: ~3.0.2
  espressif/esp_audio_effects: ~1.2.1
  espressif/esp_audio_codec: ~2.4.1
-  78/esp-ml307: ~3.6.3
+  78/esp-ml307: ~3.6.4
  78/uart-eth-modem:
-    version: ~0.3.1
+    version: ~0.3.2
    rules:
    - if: target not in [esp32]
  78/xiaozhi-fonts: ~1.6.0
--- a/main/system_info.cc
+++ b/main/system_info.cc
@@ -8,6 +8,7 @@
 #include <esp_partition.h>
 #include <esp_app_desc.h>
 #include <esp_ota_ops.h>
+#include <esp_pm.h>
 #if CONFIG_IDF_TARGET_ESP32P4
 #include "esp_wifi_remote.h"
 #endif
@@ -149,3 +150,7 @@ void SystemInfo::PrintHeapStats() {
    int min_free_sram = heap_caps_get_minimum_free_size(MALLOC_CAP_INTERNAL);
    ESP_LOGI(TAG, "free sram: %u minimal sram: %u", free_sram, min_free_sram);
 }
+
+void SystemInfo::PrintPmLocks() {
+    esp_pm_dump_locks(stdout);
+}
--- a/main/system_info.h
+++ b/main/system_info.h
@@ -17,6 +17,7 @@ public:
    static esp_err_t PrintTaskCpuUsage(TickType_t xTicksToWait);
    static void PrintTaskList();
    static void PrintHeapStats();
+    static void PrintPmLocks();
 };

 #endif // _SYSTEM_INFO_H_