m5stack-cores3.yaml

substitutions:
  name: m5cores3
  friendly_name: M5CoreS3
  loading_illustration_file: https://github.com/esphome/firmware/raw/main/voice-assistant/casita/loading_320_240.png
  idle_illustration_file: https://github.com/esphome/firmware/raw/main/voice-assistant/casita/idle_320_240.png
  listening_illustration_file: https://github.com/esphome/firmware/raw/main/voice-assistant/casita/listening_320_240.png
  thinking_illustration_file: https://github.com/esphome/firmware/raw/main/voice-assistant/casita/thinking_320_240.png
  replying_illustration_file: https://github.com/esphome/firmware/raw/main/voice-assistant/casita/replying_320_240.png
  error_illustration_file: https://github.com/esphome/firmware/raw/main/voice-assistant/casita/error_320_240.png

  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_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'

esphome:
  name: m5cores3
  friendly_name: M5CoreS3
  project:
    name: m5stack.cores3-voice-assistant
    version: "1.0"
  platformio_options:
    board_build.f_cpu : 240000000L
  libraries:
    - m5stack/M5GFX@^0.1.11
    - m5stack/M5Unified@^0.1.11
  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

esp32:
  board: esp32-s3-devkitc-1
  flash_size: 16MB
  framework:
    type: arduino

psram:
  mode: octal
  speed: 80MHz

external_components:
  - source:
      type: git
      url: https://github.com/m5stack/M5CoreS3-Esphome
    components: [ board_m5cores3, m5cores3_audio, m5cores3_display ]
    refresh: 0s

# Enable logging
logger:

# Enable Home Assistant API
api:
  encryption:
    # Replace the key by your API key
    key: "<YOUR_API_KEY>"
  on_client_connected:
    - script.execute: draw_display
  on_client_disconnected:
    - script.execute: draw_display

ota:
  - platform: esphome
    # Replace the key by your OTA key
    password: "<YOUR_OTA_KEY>"

wifi:
  # Enable fallback hotspot (captive portal) in case wifi connection fails
  ap:
  on_connect:
    - script.execute: draw_display
    - delay: 5s # Gives time for improv results to be transmitted 
  on_disconnect:
    - script.execute: draw_display

captive_portal:

# 
# Globals
# 
globals:
  - id: init_in_progress
    type: bool
    restore_value: no
    initial_value: 'true'
  - id: voice_assistant_phase
    type: int
    restore_value: no
    initial_value: ${voice_assist_not_ready_phase_id}

# 
# Display
# 
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(m5cores3_lcd).show_page(listening_page);
                                id(m5cores3_lcd).update();
                                break;
                              case ${voice_assist_thinking_phase_id}:
                                id(m5cores3_lcd).show_page(thinking_page);
                                id(m5cores3_lcd).update();
                                break;
                              case ${voice_assist_replying_phase_id}:
                                id(m5cores3_lcd).show_page(replying_page);
                                id(m5cores3_lcd).update();
                                break;
                              case ${voice_assist_error_phase_id}:
                                id(m5cores3_lcd).show_page(error_page);
                                id(m5cores3_lcd).update();
                                break;
                              case ${voice_assist_muted_phase_id}:
                                id(m5cores3_lcd).show_page(muted_page);
                                id(m5cores3_lcd).update();
                                break;
                              case ${voice_assist_not_ready_phase_id}:
                                id(m5cores3_lcd).show_page(no_ha_page);
                                id(m5cores3_lcd).update();
                                break;
                              default:
                                id(m5cores3_lcd).show_page(idle_page);
                                id(m5cores3_lcd).update();
                            }
                      else:
                        - display.page.show: no_ha_page
                        - component.update: m5cores3_lcd
                else:
                  - display.page.show: no_wifi_page
                  - component.update: m5cores3_lcd
          else:
            - display.page.show: initializing_page
            - component.update: m5cores3_lcd

image:
  - file: ${error_illustration_file}
    id: casita_error
    resize: 320x240
    type: RGB
  - file: ${idle_illustration_file}
    id: casita_idle
    resize: 320x240
    type: RGB
  - file: ${listening_illustration_file}
    id: casita_listening
    resize: 320x240
    type: RGB
  - file: ${thinking_illustration_file}
    id: casita_thinking
    resize: 320x240
    type: RGB
  - file: ${replying_illustration_file}
    id: casita_replying
    resize: 320x240
    type: RGB
  - file: ${loading_illustration_file}
    id: casita_initializing
    resize: 320x240
    type: RGB
  - file: https://github.com/esphome/firmware/raw/main/voice-assistant/error_box_illustrations/error-no-wifi.png
    id: error_no_wifi
    resize: 320x240
    type: RGB
  - file: https://github.com/esphome/firmware/raw/main/voice-assistant/error_box_illustrations/error-no-ha.png
    id: error_no_ha
    resize: 320x240
    type: RGB
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}

display:
  - platform: m5cores3_display
    model: ILI9342
    dc_pin: 35
    update_interval: never
    id: m5cores3_lcd
    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: listening_page
        lambda: |-
          it.fill(id(listening_color));
          it.image((it.get_width() / 2), (it.get_height() / 2), id(casita_listening), ImageAlign::CENTER);
      - id: thinking_page
        lambda: |-
          it.fill(id(thinking_color));
          it.image((it.get_width() / 2), (it.get_height() / 2), id(casita_thinking), ImageAlign::CENTER);
      - id: replying_page
        lambda: |-
          it.fill(id(replying_color));
          it.image((it.get_width() / 2), (it.get_height() / 2), id(casita_replying), 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);

# 
# Audio
# 
board_m5cores3:
m5cores3_audio:
  id: m5cores3_audio_1

microphone:
  - platform: m5cores3_audio
    m5cores3_audio_id: m5cores3_audio_1
    id: m5cores3_mic
    adc_type: external
    i2s_din_pin: 14
    pdm: false

speaker:
  - platform: m5cores3_audio
    m5cores3_audio_id: m5cores3_audio_1
    id: m5cores3_spk
    dac_type: external
    i2s_dout_pin: 13
    mode: mono

# 
# VA
# 
voice_assistant:
  id: va
  microphone: m5cores3_mic
  speaker: m5cores3_spk
  use_wake_word: true
  noise_suppression_level: 2
  auto_gain: 31dBFS
  volume_multiplier: 2.0
  # vad_threshold: 3
  on_listening:
    - lambda: id(voice_assistant_phase) = ${voice_assist_listening_phase_id};
    - script.execute: draw_display
  on_stt_vad_end:
    - lambda: id(voice_assistant_phase) = ${voice_assist_thinking_phase_id};
    - script.execute: draw_display
  on_tts_stream_start:
    - lambda: id(voice_assistant_phase) = ${voice_assist_replying_phase_id};
    - script.execute: draw_display
  on_tts_stream_end:
    - lambda: id(voice_assistant_phase) = ${voice_assist_idle_phase_id};
    - script.execute: draw_display
  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
          - if:
              condition:
                switch.is_off: mute
              then:
                - lambda: id(voice_assistant_phase) = ${voice_assist_idle_phase_id};
              else:
                - lambda: id(voice_assistant_phase) = ${voice_assist_muted_phase_id};
          - script.execute: draw_display
  on_client_connected: 
    - if:
        condition:
          switch.is_off: mute
        then:
          - voice_assistant.start_continuous:
          - lambda: id(voice_assistant_phase) = ${voice_assist_idle_phase_id};
        else:
          - lambda: id(voice_assistant_phase) = ${voice_assist_muted_phase_id};
    - lambda: id(init_in_progress) = false; 
    - script.execute: draw_display
  on_client_disconnected:
    - lambda: id(voice_assistant_phase) = ${voice_assist_not_ready_phase_id};  
    - script.execute: draw_display

switch:
- platform: template
  name: "LCD Backlight"
  id: switch_lcd_backlight
  restore_mode: "RESTORE_DEFAULT_ON"
  turn_on_action:
    - lambda:
        M5.Display.setBrightness(127);
  turn_off_action:
    - lambda: |-
        M5.Display.setBrightness(0);
- platform: template
  name: Mute
  id: mute
  optimistic: true
  restore_mode: RESTORE_DEFAULT_OFF
  entity_category: config
  on_turn_off:
    - if:
        condition:
          lambda: return !id(init_in_progress);
        then:      
          - lambda: id(va).set_use_wake_word(true);
          - lambda: id(voice_assistant_phase) = ${voice_assist_idle_phase_id};
          - if:
              condition:
                not:
                  - voice_assistant.is_running
              then:
                - voice_assistant.start_continuous
          - script.execute: draw_display
  on_turn_on:
    - if:
        condition:
          lambda: return !id(init_in_progress);
        then:      
          - voice_assistant.stop
          - lambda: id(va).set_use_wake_word(false);
          - lambda: id(voice_assistant_phase) = ${voice_assist_muted_phase_id};
          - script.execute: draw_display