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- Updated README.md to remove outdated camera sensor configuration instructions.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.

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");
 }
 

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() {

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;

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");
 }
 

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");
 }
 

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");
 }
 

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");
 }
 

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");
 }
 

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) {

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();