Espressif ESP32-S3-BOX-3 Voice Assistant¶

# file: esphome/examples/esp32-s3-box-3-voice-assistant.yaml
# section: substitutions
substitutions:
  device_name: "${timer_area}-voice-assistant"
  friendly_name: "${timer_area} Voice Assistant"
  device_description: "ESP32-S3-BOX-3"

  # REQUIRED: Set this to match your HA area
  timer_area: "playroom"

  # Generic voice assistant images
  loading_illustration_file: https://github.com/esphome/wake-word-voice-assistants/raw/main/casita/loading_320_240.png
  idle_illustration_file: https://github.com/esphome/wake-word-voice-assistants/raw/main/casita/idle_320_240.png
  listening_illustration_file: https://github.com/esphome/wake-word-voice-assistants/raw/main/casita/listening_320_240.png
  thinking_illustration_file: https://github.com/esphome/wake-word-voice-assistants/raw/main/casita/thinking_320_240.png
  replying_illustration_file: https://github.com/esphome/wake-word-voice-assistants/raw/main/casita/replying_320_240.png
  error_illustration_file: https://github.com/esphome/wake-word-voice-assistants/raw/main/casita/error_320_240.png
  timer_finished_illustration_file: https://github.com/esphome/wake-word-voice-assistants/raw/main/casita/timer_finished_320_240.png

  # Background colors
  loading_illustration_background_color: "000000"
  idle_illustration_background_color: "000000"
  listening_illustration_background_color: "FFFFFF"
  thinking_illustration_background_color: "FFFFFF"
  replying_illustration_background_color: "FFFFFF"
  error_illustration_background_color: "000000"

  # Voice assistant phase IDs
  voice_assist_idle_phase_id: "1"
  voice_assist_listening_phase_id: "2"
  voice_assist_thinking_phase_id: "3"
  voice_assist_replying_phase_id: "4"
  voice_assist_not_ready_phase_id: "10"
  voice_assist_error_phase_id: "11"
  voice_assist_muted_phase_id: "12"
  voice_assist_timer_finished_phase_id: "20"
  voice_assist_ota_phase_id: "30"

  # Font configuration
  allowed_characters: " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~°"
  font_glyphsets: "GF_Latin_Core"
  font_family: Figtree

# file: esphome/examples/esp32-s3-box-3-voice-assistant.yaml
# section: esphome
esphome:
  name: ${device_name}
  friendly_name: ${friendly_name}
  comment: ${device_description}
  min_version: 2025.5.0
  name_add_mac_suffix: false
  on_boot:
    - priority: 600
      then:
        - script.execute: draw_display
        - delay: 30s
        - if:
            condition:
              lambda: return id(init_in_progress);
            then:
              - lambda: id(init_in_progress) = false;
              - script.execute: draw_display

# file: esphome/examples/esp32-s3-box-3-voice-assistant.yaml
# section: esp32
esp32:
  board: esp32s3box
  flash_size: 16MB
  cpu_frequency: 240MHz
  framework:
    type: esp-idf
    sdkconfig_options:
      CONFIG_ESP32S3_DEFAULT_CPU_FREQ_240: "y"
      CONFIG_ESP32S3_DATA_CACHE_64KB: "y"
      CONFIG_ESP32S3_DATA_CACHE_LINE_64B: "y"

psram:
  mode: octal
  speed: 80MHz

# file: esphome/examples/esp32-s3-box-3-voice-assistant.yaml
# section: api
api:
  on_client_connected:
    - script.execute: draw_display
  on_client_disconnected:
    - script.execute: draw_display

  services:
    - service: timer_finished
      then:
        - logger.log: "Timer finished! Playing alarm..."
        - switch.turn_on: timer_ringing

    - service: timer_started
      variables:
        duration: int
      then:
        - logger.log:
            format: "Timer started with duration: %d seconds"
            args: ["duration"]
        - script.execute: draw_display

    - service: timer_cancelled
      then:
        - logger.log: "Timer cancelled"
        - switch.turn_off: timer_ringing
        - script.execute: draw_display

    - service: stop_alarm
      then:
        - switch.turn_off: timer_ringing

# file: esphome/examples/esp32-s3-box-3-voice-assistant.yaml
# section: ota
ota:
  - platform: esphome
    id: ota_esphome
    on_begin:
      - script.execute: stop_wake_word
      - lambda: |-
          id(voice_assistant_phase) = ${voice_assist_ota_phase_id};
          id(ota_progress) = 0;
      - display.page.show: ota_page
      - component.update: s3_box_lcd
    on_progress:
      - lambda: id(ota_progress) = (int)x;
      - component.update: s3_box_lcd
    on_end:
      - lambda: id(ota_progress) = 100;
      - component.update: s3_box_lcd
    on_error:
      - lambda: id(ota_progress) = -1;
      - display.page.show: error_page
      - component.update: s3_box_lcd
      - delay: 5s
      - script.execute: draw_display

logger:
  level: DEBUG
  hardware_uart: USB_SERIAL_JTAG
  logs:
    text_sensor: WARN
    sensor: WARN
    component: ERROR

wifi:
  ssid: !secret wifi_ssid
  password: !secret wifi_password
  on_connect:
    - script.execute: draw_display
  on_disconnect:
    - script.execute: draw_display

time:
  - platform: sntp
    id: sntp_time
    servers: !secret ntp_servers
    timezone: !secret timezone

# file: esphome/examples/esp32-s3-box-3-voice-assistant.yaml
# section: interval
interval:
  - interval: 30s
    then:
      - lambda: |-
          if (id(voice_assistant_phase) == ${voice_assist_idle_phase_id} ||
              id(voice_assistant_phase) == ${voice_assist_muted_phase_id}) {
            std::string state = id(timer_state).state;
            if (state == "active" || state == "paused") {
              ESP_LOGD("timer_sync", "Timer is %s but display is idle - triggering redraw", state.c_str());
              id(draw_display).execute();
            }
          }

# file: esphome/examples/esp32-s3-box-3-voice-assistant.yaml
# section: button
button:
  - platform: restart
    id: restart_btn
    name: Restart

  - platform: factory_reset
    id: factory_reset_btn
    internal: true

# file: esphome/examples/esp32-s3-box-3-voice-assistant.yaml
# section: sensor
sensor:
  - platform: template
    name: "Voice Assistant Phase"
    id: voice_assistant_phase_sensor
    lambda: |-
      return (float)id(voice_assistant_phase);
    update_interval: 500ms

  - platform: homeassistant
    id: timer_remaining
    name: "Timer remaining"
    entity_id: sensor.${timer_area}_timer_remaining_seconds
    unit_of_measurement: "s"
    device_class: "duration"
    on_value:
      then:
        - script.execute: draw_display

  - platform: homeassistant
    id: timer_duration
    name: "Timer duration"
    entity_id: sensor.${timer_area}_timer_remaining_seconds
    attribute: duration_seconds
    unit_of_measurement: "s"
    device_class: "duration"

  - platform: homeassistant
    id: timer_progress
    entity_id: sensor.${timer_area}_timer_remaining_seconds
    attribute: progress_percent
    internal: true

  - platform: aht10
    i2c_id: bus_b
    variant: AHT20
    temperature:
      name: "Temperature"
      id: s3temp
    humidity:
      name: "Humidity"
    update_interval: 60s

  - platform: adc
    pin: GPIO10
    id: battery_voltage
    unit_of_measurement: "V"
    accuracy_decimals: 1
    device_class: "voltage"
    entity_category: "diagnostic"
    update_interval: 30s
    attenuation: auto
    filters:
      - multiply: 4.11

  - platform: copy
    id: battery_percent
    source_id: battery_voltage
    name: "Battery level"
    unit_of_measurement: "%"
    accuracy_decimals: 0
    device_class: "battery"
    entity_category: "diagnostic"
    filters:
      - lambda: return (x - 2.7) / (4.2 - 2.7) * 100;
      - clamp:
          min_value: 0
          max_value: 100

  - platform: wifi_signal
    name: "WiFi db"
    id: wifi_signal_db
    update_interval: 30s

  - platform: copy
    source_id: wifi_signal_db
    name: "WiFi Signal"
    id: wifi_percent
    filters:
      - lambda: return min(max(2 * (x + 100.0), 0.0), 100.0);
    unit_of_measurement: "%"
    entity_category: "diagnostic"

# file: esphome/examples/esp32-s3-box-3-voice-assistant.yaml
# section: touchscreen
touchscreen:
  - platform: gt911
    i2c_id: bus_a
    address: 0x5D
    id: gt911_touchscreen
    interrupt_pin:
      number: GPIO3
      ignore_strapping_warning: true

# file: esphome/examples/esp32-s3-box-3-voice-assistant.yaml
# section: binary_sensor
binary_sensor:
  - platform: gpio
    pin:
      number: GPIO21
    name: "Presence detect"
    device_class: "occupancy"

  - platform: gt911
    id: touch_area
    index: 0
    on_press:
      then:
        - if:
            condition:
              lambda: return !id(init_in_progress);
            then:
              - if:
                  condition:
                    switch.is_on: timer_ringing
                  then:
                    - switch.turn_off: timer_ringing
                  else:
                    - if:
                        condition:
                          voice_assistant.is_running:
                        then:
                          - voice_assistant.stop:
                        else:
                          - if:
                              condition:
                                media_player.is_announcing:
                              then:
                                media_player.stop:
                                  announcement: true
                              else:
                                - if:
                                    condition:
                                      media_player.is_playing:
                                    then:
                                      - media_player.pause:
                                    else:
                                      - if:
                                          condition:
                                            and:
                                              - lambda: return !id(is_muted);
                                              - not: voice_assistant.is_running
                                          then:
                                            - media_player.speaker.play_on_device_media_file:
                                                media_file: wake_word_triggered_sound_file
                                                announcement: true
                                            - wait_until:
                                                - not:
                                                    - media_player.is_announcing:
                                            - voice_assistant.start:

  - platform: gpio
    pin:
      number: GPIO0
      mode: INPUT_PULLUP
      inverted: true
    id: left_top_button
    internal: true
    on_multi_click:
      - timing:
          - ON for at least 50ms
          - OFF for at least 50ms
        then:
          - switch.turn_off: timer_ringing
      - timing:
          - ON for at least 10s
        then:
          - button.press: factory_reset_btn

  - platform: gpio
    pin:
      number: GPIO1
      mode: INPUT_PULLUP
      inverted: true
    id: mute_button
    name: "Mute Button"
    internal: true
    trigger_on_initial_state: true
    on_press:
      then:
        - script.execute: enable_mute
    on_release:
      then:
        - script.execute: disable_mute

# file: esphome/examples/esp32-s3-box-3-voice-assistant.yaml
# section: i2c
i2c:
  - id: bus_a
    sda: GPIO08
    scl: GPIO18
    scan: true
    sda_pullup_enabled: true
    scl_pullup_enabled: true
    frequency: 100kHz
  - sda: GPIO41
    scl: GPIO40
    scan: true
    sda_pullup_enabled: true
    scl_pullup_enabled: true
    frequency: 50kHz
    id: bus_b

# file: esphome/examples/esp32-s3-box-3-voice-assistant.yaml
# section: audio
i2s_audio:
  - id: i2s_audio_bus
    i2s_lrclk_pin: GPIO45
    i2s_bclk_pin: GPIO17
    i2s_mclk_pin: GPIO2

audio_adc:
  - platform: es7210
    id: es7210_adc
    bits_per_sample: 16bit
    sample_rate: 16000
    i2c_id: bus_a

audio_dac:
  - platform: es8311
    id: es8311_dac
    bits_per_sample: 16bit
    sample_rate: 48000
    i2c_id: bus_a

microphone:
  - platform: i2s_audio
    id: box_mic
    sample_rate: 16000
    i2s_din_pin: GPIO16
    bits_per_sample: 16bit
    adc_type: external

speaker:
  - id: i2s_audio_speaker
    platform: i2s_audio
    i2s_audio_id: i2s_audio_bus
    i2s_dout_pin: GPIO15
    dac_type: external
    sample_rate: 48000
    bits_per_sample: 16bit
    channel: left
    audio_dac: es8311_dac
    buffer_duration: 100ms

media_player:
  - platform: speaker
    name: None
    id: speaker_media_player
    volume_min: 0.5
    volume_max: 0.8
    task_stack_in_psram: true
    announcement_pipeline:
      speaker: i2s_audio_speaker
      format: FLAC
      sample_rate: 48000
      num_channels: 1
    files:
      - id: timer_finished_sound
        file: https://github.com/esphome/home-assistant-voice-pe/raw/dev/sounds/timer_finished.flac
      - id: wake_word_triggered_sound_file
        file: https://github.com/esphome/home-assistant-voice-pe/raw/dev/sounds/wake_word_triggered.flac
    on_announcement:
      - lambda: id(announcement_in_progress) = true;
      - script.execute: track_announcement_lifecycle
      - if:
          condition:
            - microphone.is_capturing:
          then:
            - script.execute: stop_wake_word
      - if:
          condition:
            and:
              - not:
                  voice_assistant.is_running:
              - switch.is_off: timer_ringing
          then:
            - lambda: id(voice_assistant_phase) = ${voice_assist_muted_phase_id};
            - script.execute: draw_display
    on_idle:
      - delay: 100ms
      - if:
          condition:
            and:
              - not:
                  voice_assistant.is_running:
              - switch.is_off: timer_ringing
              - not:
                  media_player.is_announcing:
              - lambda: return !id(announcement_in_progress);
          then:
            - script.execute: start_wake_word
            - script.execute: set_idle_or_mute_phase
            - script.execute: draw_display

# file: esphome/examples/esp32-s3-box-3-voice-assistant.yaml
# section: wake_word
micro_wake_word:
  id: mww
  models:
    - model: okay_nabu
      id: okay_nabu
    - model: https://github.com/kahrendt/microWakeWord/releases/download/stop/stop.json
      id: stop
      internal: true
  vad:
    model: github://esphome/micro-wake-word-models/models/v2/vad.json
  on_wake_word_detected:
    - voice_assistant.start:
        wake_word: !lambda return wake_word;

voice_assistant:
  id: va
  microphone: box_mic
  media_player: speaker_media_player
  micro_wake_word: mww
  noise_suppression_level: 2
  auto_gain: 31dBFS
  volume_multiplier: 2.0
  on_listening:
    - lambda: id(voice_assistant_phase) = ${voice_assist_listening_phase_id};
    - text_sensor.template.publish:
        id: text_request
        state: "..."
    - text_sensor.template.publish:
        id: text_response
        state: "..."
    - script.execute: draw_display
  on_stt_vad_end:
    - lambda: id(voice_assistant_phase) = ${voice_assist_thinking_phase_id};
    - script.execute: draw_display
  on_stt_end:
    - text_sensor.template.publish:
        id: text_request
        state: !lambda return x;
    - script.execute: draw_display
  on_tts_start:
    - text_sensor.template.publish:
        id: text_response
        state: !lambda return x;
    - lambda: id(voice_assistant_phase) = ${voice_assist_replying_phase_id};
    - script.execute: draw_display
  on_end:
    - if:
        condition:
          - lambda: return id(announcement_in_progress);
        then:
          - logger.log: "on_end: Skipping - announcement in progress"
        else:
          - wait_until:
              condition:
                - media_player.is_announcing:
              timeout: 3s
          - wait_until:
              - and:
                  - not:
                      media_player.is_announcing:
                  - not:
                      speaker.is_playing:
          - lambda: id(va).set_use_wake_word(false);
          - micro_wake_word.start:
          - script.execute: set_idle_or_mute_phase
          - script.execute: draw_display
    - text_sensor.template.publish:
        id: text_request
        state: ""
    - text_sensor.template.publish:
        id: text_response
        state: ""
  on_error:
    - if:
        condition:
          lambda: return !id(init_in_progress);
        then:
          - lambda: id(voice_assistant_phase) = ${voice_assist_error_phase_id};
          - script.execute: draw_display
          - delay: 1s
          - script.execute: set_idle_or_mute_phase
          - script.execute: draw_display
  on_client_connected:
    - lambda: id(init_in_progress) = false;
    - script.execute: start_wake_word
    - script.execute: set_idle_or_mute_phase
    - script.execute: draw_display
  on_client_disconnected:
    - script.execute: stop_wake_word
    - lambda: id(voice_assistant_phase) = ${voice_assist_not_ready_phase_id};
    - script.execute: draw_display

  # Timer Event Stubs - HA handles actual timer logic
  on_timer_started:
    - logger.log:
        format: "Timer started (handled by HA): %s"
        args: ["timer.id.c_str()"]
  on_timer_finished:
    - logger.log: "Timer finished event received (handled by HA automation)"
  on_timer_cancelled:
    - logger.log: "Timer cancelled (handled by HA)"
  on_timer_updated:
    - logger.log: "Timer updated (handled by HA)"
  on_timer_tick:
    - lambda: return;

# file: esphome/examples/esp32-s3-box-3-voice-assistant.yaml
# section: text_sensor
text_sensor:
  - platform: template
    name: "Voice Assistant State"
    id: voice_assistant_state_sensor
    lambda: |-
      int phase = id(voice_assistant_phase);
      switch(phase) {
        case ${voice_assist_idle_phase_id}: return {"idle"};
        case ${voice_assist_listening_phase_id}: return {"listening"};
        case ${voice_assist_thinking_phase_id}: return {"thinking"};
        case ${voice_assist_replying_phase_id}: return {"replying"};
        case ${voice_assist_error_phase_id}: return {"error"};
        case ${voice_assist_not_ready_phase_id}: return {"not_ready"};
        case ${voice_assist_muted_phase_id}: return {"muted"};
        case ${voice_assist_timer_finished_phase_id}: return {"timer_finished"};
        default: return {"unknown"};
      }
    update_interval: 500ms

  - platform: homeassistant
    id: timer_state
    entity_id: sensor.${timer_area}_timer_remaining_seconds
    attribute: timer_state
    internal: true
    on_value:
      then:
        - script.execute: draw_display

  - id: text_request
    platform: template
    on_value:
      lambda: |-
        if(id(text_request).state.length()>32) {
          std::string name = id(text_request).state.c_str();
          std::string truncated = esphome::str_truncate(name.c_str(),31);
          id(text_request).state = (truncated+"...").c_str();
        }

  - id: text_response
    platform: template
    on_value:
      lambda: |-
        if(id(text_response).state.length()>32) {
          std::string name = id(text_response).state.c_str();
          std::string truncated = esphome::str_truncate(name.c_str(),31);
          id(text_response).state = (truncated+"...").c_str();
        }

# file: esphome/examples/esp32-s3-box-3-voice-assistant.yaml
# section: switch
output:
  - platform: ledc
    pin: GPIO47
    id: backlight_output

light:
  - platform: monochromatic
    id: led
    name: Screen
    icon: "mdi:television"
    entity_category: config
    output: backlight_output
    restore_mode: RESTORE_DEFAULT_ON
    default_transition_length: 250ms

switch:
  - platform: gpio
    name: Speaker Enable
    pin: GPIO46
    restore_mode: RESTORE_DEFAULT_ON
    entity_category: config
    disabled_by_default: true

  - platform: template
    name: Mute
    id: mute
    icon: "mdi:microphone-off"
    optimistic: false
    restore_mode: RESTORE_DEFAULT_OFF
    entity_category: config
    lambda: |-
      return id(is_muted);
    turn_on_action:
      - if:
          condition:
            lambda: return !id(is_muted);
          then:
            - script.execute: toggle_mute
    turn_off_action:
      - if:
          condition:
            lambda: return id(is_muted);
          then:
            - script.execute: toggle_mute

  - platform: template
    id: timer_ringing
    name: "Timer Ringing"
    icon: "mdi:bell-ring-outline"
    optimistic: true
    restore_mode: ALWAYS_OFF
    on_turn_off:
      - lambda: |-
          id(speaker_media_player)
            ->make_call()
            .set_command(media_player::MediaPlayerCommand::MEDIA_PLAYER_COMMAND_REPEAT_OFF)
            .set_announcement(true)
            .perform();
          id(speaker_media_player)->set_playlist_delay_ms(speaker::AudioPipelineType::ANNOUNCEMENT, 0);
      - media_player.stop:
          announcement: true
      - script.execute: set_idle_or_mute_phase
      - script.execute: draw_display
    on_turn_on:
      - lambda: id(voice_assistant_phase) = ${voice_assist_timer_finished_phase_id};
      - script.execute: draw_display
      - lambda: |-
          id(speaker_media_player)
            ->make_call()
            .set_command(media_player::MediaPlayerCommand::MEDIA_PLAYER_COMMAND_REPEAT_ONE)
            .set_announcement(true)
            .perform();
          id(speaker_media_player)->set_playlist_delay_ms(speaker::AudioPipelineType::ANNOUNCEMENT, 1000);
      - media_player.speaker.play_on_device_media_file:
          media_file: timer_finished_sound
          announcement: true
      - delay: 15min
      - switch.turn_off: timer_ringing

# file: esphome/examples/esp32-s3-box-3-voice-assistant.yaml
# section: globals
globals:
  - id: init_in_progress
    type: bool
    restore_value: false
    initial_value: "true"
  - id: voice_assistant_phase
    type: int
    restore_value: false
    initial_value: ${voice_assist_not_ready_phase_id}
  - id: ota_progress
    type: int
    restore_value: false
    initial_value: "0"
  - id: announcement_in_progress
    type: bool
    restore_value: false
    initial_value: "false"
  - id: is_muted
    type: bool
    restore_value: false
    initial_value: "false"

# file: esphome/examples/esp32-s3-box-3-voice-assistant.yaml
# section: script
script:
  - id: draw_display
    then:
      - if:
          condition:
            lambda: return !id(init_in_progress);
          then:
            - if:
                condition:
                  wifi.connected:
                then:
                  - if:
                      condition:
                        api.connected:
                      then:
                        - lambda: |
                            switch(id(voice_assistant_phase)) {
                              case ${voice_assist_listening_phase_id}:
                                id(s3_box_lcd).show_page(listening_page);
                                id(s3_box_lcd).update();
                                break;
                              case ${voice_assist_thinking_phase_id}:
                                id(s3_box_lcd).show_page(thinking_page);
                                id(s3_box_lcd).update();
                                break;
                              case ${voice_assist_replying_phase_id}:
                                id(s3_box_lcd).show_page(replying_page);
                                id(s3_box_lcd).update();
                                break;
                              case ${voice_assist_error_phase_id}:
                                id(s3_box_lcd).show_page(error_page);
                                id(s3_box_lcd).update();
                                break;
                              case ${voice_assist_muted_phase_id}:
                                id(s3_box_lcd).show_page(muted_page);
                                id(s3_box_lcd).update();
                                break;
                              case ${voice_assist_not_ready_phase_id}:
                                id(s3_box_lcd).show_page(no_ha_page);
                                id(s3_box_lcd).update();
                                break;
                              case ${voice_assist_timer_finished_phase_id}:
                                id(s3_box_lcd).show_page(timer_finished_page);
                                id(s3_box_lcd).update();
                                break;
                              case ${voice_assist_ota_phase_id}:
                                id(s3_box_lcd).show_page(ota_page);
                                id(s3_box_lcd).update();
                                break;
                              default:
                                id(s3_box_lcd).show_page(idle_page);
                                id(s3_box_lcd).update();
                            }
                      else:
                        - display.page.show: no_ha_page
                        - component.update: s3_box_lcd
                else:
                  - display.page.show: no_wifi_page
                  - component.update: s3_box_lcd
          else:
            - display.page.show: initializing_page
            - component.update: s3_box_lcd

  - id: draw_timer_timeline
    then:
      - lambda: |
          std::string state = id(timer_state).state;
          int remaining = (int)id(timer_remaining).state;
          int duration = (int)id(timer_duration).state;

          if (state == "active" && duration > 0 && remaining > 0) {
            int active_pixels = (320 * remaining) / duration;
            if (active_pixels > 0) {
              id(s3_box_lcd).filled_rectangle(0, 225, 320, 15, Color::WHITE);
              id(s3_box_lcd).filled_rectangle(0, 226, active_pixels, 13, id(active_timer_color));
            }
          } else if (state == "paused" && duration > 0 && remaining > 0) {
            int active_pixels = (320 * remaining) / duration;
            if (active_pixels > 0) {
              id(s3_box_lcd).filled_rectangle(0, 225, 320, 15, Color::WHITE);
              id(s3_box_lcd).filled_rectangle(0, 226, active_pixels, 13, id(paused_timer_color));
            }
          }

  - id: draw_active_timer_widget
    then:
      - lambda: |
          std::string state = id(timer_state).state;
          int remaining = (int)id(timer_remaining).state;

          if (state == "active" || state == "paused") {
            id(s3_box_lcd).filled_rectangle(80, 40, 160, 50, Color::WHITE);
            id(s3_box_lcd).rectangle(80, 40, 160, 50, Color::BLACK);

            int hours_left = remaining / 3600;
            int minutes_left = (remaining - hours_left * 3600) / 60;
            int seconds_left = remaining - hours_left * 3600 - minutes_left * 60;

            auto display_hours = (hours_left < 10 ? "0" : "") + std::to_string(hours_left);
            auto display_minute = (minutes_left < 10 ? "0" : "") + std::to_string(minutes_left);
            auto display_seconds = (seconds_left < 10 ? "0" : "") + std::to_string(seconds_left);

            std::string display_string = "";
            if (hours_left > 0) {
              display_string = display_hours + ":" + display_minute;
            } else {
              display_string = display_minute + ":" + display_seconds;
            }
            id(s3_box_lcd).printf(120, 47, id(font_timer), Color::BLACK, "%s", display_string.c_str());
          }

  - id: enable_mute
    mode: single
    then:
      - script.execute: stop_wake_word
      - delay: 100ms
      - microphone.mute:
      - lambda: id(is_muted) = true;
      - switch.template.publish:
          id: mute
          state: ON
      - lambda: id(voice_assistant_phase) = ${voice_assist_muted_phase_id};
      - script.execute: draw_display

  - id: disable_mute
    mode: single
    then:
      - lambda: id(is_muted) = false;
      - switch.template.publish:
          id: mute
          state: OFF
      - lambda: id(voice_assistant_phase) = ${voice_assist_idle_phase_id};
      - script.execute: draw_display
      - microphone.unmute:
      - delay: 100ms
      - script.execute: start_wake_word

  - id: toggle_mute
    mode: restart
    then:
      - if:
          condition:
            lambda: return id(is_muted);
          then:
            - lambda: id(is_muted) = false;
            - switch.template.publish:
                id: mute
                state: OFF
            - lambda: id(voice_assistant_phase) = ${voice_assist_idle_phase_id};
            - script.execute: draw_display
            - microphone.unmute:
            - delay: 100ms
            - script.execute: start_wake_word
          else:
            - script.execute: stop_wake_word
            - delay: 100ms
            - microphone.mute:
            - lambda: id(is_muted) = true;
            - switch.template.publish:
                id: mute
                state: ON
            - lambda: id(voice_assistant_phase) = ${voice_assist_muted_phase_id};
            - script.execute: draw_display

  - id: start_wake_word
    then:
      - if:
          condition:
            lambda: return !id(is_muted);
          then:
            - if:
                condition:
                  not:
                    - voice_assistant.is_running:
                then:
                  - lambda: id(va).set_use_wake_word(false);
                  - micro_wake_word.start:

  - id: stop_wake_word
    then:
      - micro_wake_word.stop:

  - id: set_idle_or_mute_phase
    then:
      - if:
          condition:
            lambda: return !id(is_muted);
          then:
            - lambda: id(voice_assistant_phase) = ${voice_assist_idle_phase_id};
          else:
            - lambda: id(voice_assistant_phase) = ${voice_assist_muted_phase_id};

  - id: track_announcement_lifecycle
    mode: restart
    then:
      - logger.log: "Announcement lifecycle: waiting for audio to start..."
      - wait_until:
          condition:
            - media_player.is_announcing:
          timeout: 30s
      - if:
          condition:
            - not:
                media_player.is_announcing:
          then:
            - logger.log: "Announcement lifecycle: timed out waiting for audio"
            - lambda: id(announcement_in_progress) = false;
          else:
            - logger.log: "Announcement lifecycle: audio playing, waiting for completion..."
            - wait_until:
                condition:
                  - not:
                      media_player.is_announcing:
                timeout: 10min
            - logger.log: "Announcement lifecycle: complete"
            - lambda: id(announcement_in_progress) = false;

# file: esphome/examples/esp32-s3-box-3-voice-assistant.yaml
# section: image
image:
  - file: ${error_illustration_file}
    id: casita_error
    resize: 320x240
    type: RGB
    transparency: alpha_channel
  - file: ${idle_illustration_file}
    id: casita_idle
    resize: 320x240
    type: RGB
    transparency: alpha_channel
  - file: ${listening_illustration_file}
    id: casita_listening
    resize: 320x240
    type: RGB
    transparency: alpha_channel
  - file: ${thinking_illustration_file}
    id: casita_thinking
    resize: 320x240
    type: RGB
    transparency: alpha_channel
  - file: ${replying_illustration_file}
    id: casita_replying
    resize: 320x240
    type: RGB
    transparency: alpha_channel
  - file: ${timer_finished_illustration_file}
    id: casita_timer_finished
    resize: 320x240
    type: RGB
    transparency: alpha_channel
  - file: ${loading_illustration_file}
    id: casita_initializing
    resize: 320x240
    type: RGB
    transparency: alpha_channel
  - file: https://github.com/esphome/wake-word-voice-assistants/raw/main/error_box_illustrations/error-no-wifi.png
    id: error_no_wifi
    resize: 320x240
    type: RGB
    transparency: alpha_channel
  - file: https://github.com/esphome/wake-word-voice-assistants/raw/main/error_box_illustrations/error-no-ha.png
    id: error_no_ha
    resize: 320x240
    type: RGB
    transparency: alpha_channel

# file: esphome/examples/esp32-s3-box-3-voice-assistant.yaml
# section: font
font:
  - file:
      type: gfonts
      family: ${font_family}
      weight: 300
      italic: true
    id: font_request
    size: 15
    glyphsets:
      - ${font_glyphsets}
  - file:
      type: gfonts
      family: ${font_family}
      weight: 300
    id: font_response
    size: 15
    glyphsets:
      - ${font_glyphsets}
  - file:
      type: gfonts
      family: ${font_family}
      weight: 300
    id: font_timer
    size: 30
    glyphsets:
      - ${font_glyphsets}
  - file:
      type: gfonts
      family: ${font_family}
      weight: 700
    id: font_ota
    size: 24
    glyphsets:
      - ${font_glyphsets}

# file: esphome/examples/esp32-s3-box-3-voice-assistant.yaml
# section: color
color:
  - id: idle_color
    hex: ${idle_illustration_background_color}
  - id: listening_color
    hex: ${listening_illustration_background_color}
  - id: thinking_color
    hex: ${thinking_illustration_background_color}
  - id: replying_color
    hex: ${replying_illustration_background_color}
  - id: loading_color
    hex: ${loading_illustration_background_color}
  - id: error_color
    hex: ${error_illustration_background_color}
  - id: active_timer_color
    hex: "26ed3a"
  - id: paused_timer_color
    hex: "3b89e3"
  - id: ota_progress_color
    hex: "ff6600"

# file: esphome/examples/esp32-s3-box-3-voice-assistant.yaml
# section: spi
spi:
  - id: spi_bus
    clk_pin: 7
    mosi_pin: 6

# file: esphome/examples/esp32-s3-box-3-voice-assistant.yaml
# section: display
display:
  - platform: ili9xxx
    id: s3_box_lcd
    model: S3BOX
    invert_colors: false
    data_rate: 40MHz
    cs_pin: 5
    dc_pin: 4
    reset_pin:
      number: 48
      inverted: true
    update_interval: never
    pages:
      - id: idle_page
        lambda: |-
          it.fill(id(idle_color));
          it.image((it.get_width() / 2), (it.get_height() / 2), id(casita_idle), ImageAlign::CENTER);
          id(draw_timer_timeline).execute();

      - id: listening_page
        lambda: |-
          it.fill(id(listening_color));
          it.image((it.get_width() / 2), (it.get_height() / 2), id(casita_listening), ImageAlign::CENTER);
          id(draw_timer_timeline).execute();

      - id: thinking_page
        lambda: |-
          it.fill(id(thinking_color));
          it.image((it.get_width() / 2), (it.get_height() / 2), id(casita_thinking), ImageAlign::CENTER);
          it.filled_rectangle(20, 20, 280, 30, Color::WHITE);
          it.rectangle(20, 20, 280, 30, Color::BLACK);
          it.printf(30, 25, id(font_request), Color::BLACK, "%s", id(text_request).state.c_str());
          id(draw_timer_timeline).execute();

      - id: replying_page
        lambda: |-
          it.fill(id(replying_color));
          it.image((it.get_width() / 2), (it.get_height() / 2), id(casita_replying), ImageAlign::CENTER);
          it.filled_rectangle(20, 20, 280, 30, Color::WHITE);
          it.rectangle(20, 20, 280, 30, Color::BLACK);
          it.filled_rectangle(20, 190, 280, 30, Color::WHITE);
          it.rectangle(20, 190, 280, 30, Color::BLACK);
          it.printf(30, 25, id(font_request), Color::BLACK, "%s", id(text_request).state.c_str());
          it.printf(30, 195, id(font_response), Color::BLACK, "%s", id(text_response).state.c_str());
          id(draw_timer_timeline).execute();

      - id: timer_finished_page
        lambda: |-
          it.fill(id(idle_color));
          it.image((it.get_width() / 2), (it.get_height() / 2), id(casita_timer_finished), ImageAlign::CENTER);

      - id: error_page
        lambda: |-
          it.fill(id(error_color));
          it.image((it.get_width() / 2), (it.get_height() / 2), id(casita_error), ImageAlign::CENTER);

      - id: no_ha_page
        lambda: |-
          it.image((it.get_width() / 2), (it.get_height() / 2), id(error_no_ha), ImageAlign::CENTER);

      - id: no_wifi_page
        lambda: |-
          it.image((it.get_width() / 2), (it.get_height() / 2), id(error_no_wifi), ImageAlign::CENTER);

      - id: initializing_page
        lambda: |-
          it.fill(id(loading_color));
          it.image((it.get_width() / 2), (it.get_height() / 2), id(casita_initializing), ImageAlign::CENTER);

      - id: muted_page
        lambda: |-
          it.fill(Color::BLACK);
          id(draw_timer_timeline).execute();
          id(draw_active_timer_widget).execute();
      - id: ota_page
        lambda: |-
          it.fill(id(error_color));
          it.image((it.get_width() / 2), (it.get_height() / 2), id(casita_error), ImageAlign::CENTER);
          it.filled_rectangle(20, 200, 280, 30, Color::WHITE);
          it.rectangle(20, 200, 280, 30, Color::BLACK);
          int progress_width = (id(ota_progress) * 276) / 100;
          if (progress_width > 0) {
            it.filled_rectangle(22, 202, progress_width, 26, id(ota_progress_color));
          }
          if (id(ota_progress) >= 0) {
            it.printf(160, 185, id(font_ota), Color::WHITE, TextAlign::BOTTOM_CENTER, "Upgrading: %d%%", id(ota_progress));
          } else {
            it.printf(160, 185, id(font_ota), Color::WHITE, TextAlign::BOTTOM_CENTER, "Update Failed!");
          }