Add voice assistant config

config/common/buttons.yaml

@@ -105,8 +105,55 @@ binary_sensor:
           - ON for at most 1s
           - OFF for at least 0.25s
         then:
-          - logger.log: "Action-Button on_multi_click"
-
+          - if:
+              condition:
+                lambda: return !id(init_in_progress);
+              then:
+                - event.trigger:
+                    id: action_button_press_event
+                    event_type: "single_press"
+                - if:
+                    condition:
+                      switch.is_on: timer_ringing
+                    then:
+                      - switch.turn_off: timer_ringing
+                    else:
+                      - if:
+                          condition:
+                            lambda: return id(nabu_media_player)->state == media_player::MediaPlayerState::MEDIA_PLAYER_STATE_ANNOUNCING;
+                          then:
+                            - lambda: |
+                                id(nabu_media_player)
+                                  ->make_call()
+                                  .set_command(media_player::MediaPlayerCommand::MEDIA_PLAYER_COMMAND_STOP)
+                                  .set_announcement(true)
+                                  .perform();
+                          else:
+                            - if:
+                                condition:
+                                  voice_assistant.is_running:
+                                then:
+                                  - voice_assistant.stop:
+                                else:
+                                  - if:
+                                      condition:
+                                        media_player.is_playing:
+                                      then:
+                                        - media_player.pause:
+                                      else:
+                                        - if:
+                                            condition:
+                                              and:
+                                                - switch.is_off: master_mute_switch
+                                                - not:
+                                                    voice_assistant.is_running
+                                            then:
+                                              - script.execute:
+                                                  id: play_sound
+                                                  priority: true
+                                                  sound_file: !lambda return id(center_button_press_sound);
+                                              - delay: 300ms
+                                              - voice_assistant.start:
       # Double Click
       #  . Exposed as an event entity. To be used in automations inside Home Assistant
       - timing:

config/common/led_ring.yaml

@@ -44,7 +44,7 @@ script:
             id(control_leds_init_state).execute();
           } else if (!id(wifi_id).is_connected() || !id(api_id).is_connected()){
             id(control_leds_no_ha_connection_state).execute();
-          } else if (id(voice_assistant_phase) == ${voice_assist_listening_phase_id}) {
+          } else if (id(voice_assistant_phase) == ${voice_assist_waiting_for_command_phase_id}) {
             id(control_led_voice_assist_listening_phase).execute();
           } else {
             id(control_leds_idle_state).execute();

config/common/media_player.yaml

@@ -29,6 +29,23 @@ media_player:
       - script.execute: control_leds
     on_volume:
       - script.execute: control_leds
+    on_announcement:
+      - nabu.set_ducking:
+          decibel_reduction: 20
+          duration: 0.0s
+    on_state:
+      if:
+        condition:
+          and:
+            - switch.is_off: timer_ringing
+            - not:
+                voice_assistant.is_running:
+            - not:
+                lambda: return id(nabu_media_player)->state == media_player::MediaPlayerState::MEDIA_PLAYER_STATE_ANNOUNCING;
+        then:
+          - nabu.set_ducking:
+              decibel_reduction: 0
+              duration: 1.0s
 
     files:
       - id: center_button_press_sound
@@ -47,6 +64,11 @@ media_player:
         file: https://github.com/esphome/home-assistant-voice-pe/raw/dev/sounds/mute_switch_on.flac
       - id: mute_switch_off_sound
         file: https://github.com/esphome/home-assistant-voice-pe/raw/dev/sounds/mute_switch_off.flac
+      - 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: https://github.com/esphome/home-assistant-voice-pe/raw/dev/sounds/wake_word_triggered.flac
+
 
 
 script:

config/common/timer.yaml

@@ -0,0 +1,103 @@
+globals:
+  # Global variable storing the first active timer
+  - id: first_active_timer
+    type: voice_assistant::Timer
+    restore_value: false
+  # Global variable storing if a timer is active
+  - id: is_timer_active
+    type: bool
+    restore_value: false
+
+
+switch:
+  # Internal switch to track when a timer is ringing on the device.
+  - platform: template
+    id: timer_ringing
+    optimistic: true
+    internal: true
+    restore_mode: ALWAYS_OFF
+    on_turn_off:
+      # Disable stop wake word
+      # - lambda: id(stop).disable();
+      # Stop any current annoucement (ie: stop the timer ring mid playback)
+      - if:
+          condition:
+            lambda: return id(nabu_media_player)->state == media_player::MediaPlayerState::MEDIA_PLAYER_STATE_ANNOUNCING;
+          then:
+            lambda: |-
+              id(nabu_media_player)
+                ->make_call()
+                .set_command(media_player::MediaPlayerCommand::MEDIA_PLAYER_COMMAND_STOP)
+                .set_announcement(true)
+                .perform();
+      # Set back ducking ratio to zero
+      - nabu.set_ducking:
+          decibel_reduction: 0
+          duration: 1.0s
+      # Refresh the LED ring
+      - script.execute: control_leds
+    on_turn_on:
+      # Duck audio
+      - nabu.set_ducking:
+          decibel_reduction: 20
+          duration: 0.0s
+      # Enable stop wake word
+      # - lambda: id(stop).enable();
+      # Ring timer
+      - script.execute: ring_timer
+      # Refresh LED
+      - script.execute: control_leds
+      # If 15 minutes have passed and the timer is still ringing, stop it.
+      - delay: 15min
+      - switch.turn_off: timer_ringing
+
+
+script:
+  # Script executed when the timer is ringing, to playback sounds.
+  - id: ring_timer
+    then:
+      - while:
+          condition:
+            switch.is_on: timer_ringing
+          then:
+            - script.execute:
+                id: play_sound
+                priority: true
+                sound_file: !lambda return id(timer_finished_sound);
+            - wait_until:
+                lambda: |-
+                  return id(nabu_media_player)->state == media_player::MediaPlayerState::MEDIA_PLAYER_STATE_ANNOUNCING;
+            - wait_until:
+                not:
+                  lambda: |-
+                    return id(nabu_media_player)->state == media_player::MediaPlayerState::MEDIA_PLAYER_STATE_ANNOUNCING;
+
+
+  # Script used to fetch the first active timer (Stored in global first_active_timer)
+  - id: fetch_first_active_timer
+    then:
+      - lambda: |
+          const auto timers = id(va).get_timers();
+          auto output_timer = timers.begin()->second;
+          for (auto &iterable_timer : timers) {
+            if (iterable_timer.second.is_active && iterable_timer.second.seconds_left <= output_timer.seconds_left) {
+              output_timer = iterable_timer.second;
+            }
+          }
+          id(first_active_timer) = output_timer;
+
+  # Script used to check if a timer is active (Stored in global is_timer_active)
+  - id: check_if_timers_active
+    then:
+      - lambda: |
+          const auto timers = id(va).get_timers();
+          bool output = false;
+          if (timers.size() > 0) {
+            for (auto &iterable_timer : timers) {
+              if(iterable_timer.second.is_active) {
+                output = true;
+              }
+            }
+          }
+          id(is_timer_active) = output;
+

config/common/voice_assistant.yaml

@@ -1,26 +1,26 @@
 substitutions:
   # Phases of the Voice Assistant
-  # IDLE: The voice assistant is ready to be triggered by a wake-word
+  # The voice assistant is ready to be triggered by a wake word
   voice_assist_idle_phase_id: '1'
-  # LISTENING: The voice assistant is ready to listen to a voice command (after being triggered by the wake word)
-  voice_assist_listening_phase_id: '2'
-  # THINKING: The voice assistant is currently processing the command
-  voice_assist_thinking_phase_id: '3'
-  # REPLYING: The voice assistant is replying to the command
-  voice_assist_replying_phase_id: '4'
-  # NOT_READY: The voice assistant is not ready
+  # The voice assistant is waiting for a voice command (after being triggered by the wake word)
+  voice_assist_waiting_for_command_phase_id: '2'
+  # The voice assistant is listening for a voice command
+  voice_assist_listening_for_command_phase_id: '3'
+  # The voice assistant is currently processing the command
+  voice_assist_thinking_phase_id: '4'
+  # The voice assistant is replying to the command
+  voice_assist_replying_phase_id: '5'
+  # The voice assistant is not ready
   voice_assist_not_ready_phase_id: '10'
-  # ERROR: The voice assistant encountered an error
+  # The voice assistant encountered an error
   voice_assist_error_phase_id: '11'
-  # MUTED: The voice assistant is muted and will not reply to a wake-word
-  voice_assist_muted_phase_id: '12'
 
 globals:
   # Global variable tracking the phase of the voice assistant (defined above). Initialized to not_ready
   - id: voice_assistant_phase
     type: int
     restore_value: no
-    initial_value: ${voice_assist_not_ready_phase_id}
+    # initial_value: ${voice_assist_not_ready_phase_id}
 
 microphone:
   - platform: satellite1
@@ -34,11 +34,139 @@ microphone:
     adc_type: external
     gain_log2: 4
 
+
 micro_wake_word:
-  #model: github://esphome/micro-wake-word-models/models/v2/okay_nabu.json 
   models:
-    - okay_nabu
+    - model: okay_nabu
+  vad:
   on_wake_word_detected:
-    - lambda: id(voice_assistant_phase) = ${voice_assist_listening_phase_id};
+    # If the wake word is detected when the device is muted (Possible with the software mute switch): Do nothing
+    - if:
+        condition:
+          switch.is_off: master_mute_switch
+        then:
+          # If a timer is ringing: Stop it, do not start the voice assistant (We can stop timer from voice!)
+          - if:
+              condition:
+                switch.is_on: timer_ringing
+              then:
+                - switch.turn_off: timer_ringing
+              # Start voice assistant, stop current announcement.
+              else:
+                - if:
+                    condition:
+                      lambda: return id(nabu_media_player)->state == media_player::MediaPlayerState::MEDIA_PLAYER_STATE_ANNOUNCING;
+                    then:
+                      lambda: |-
+                        id(nabu_media_player)
+                          ->make_call()
+                          .set_command(media_player::MediaPlayerCommand::MEDIA_PLAYER_COMMAND_STOP)
+                          .set_announcement(true)
+                          .perform();
+                    else:
+                      - if:
+                          condition:
+                            switch.is_on: wake_sound
+                          then:
+                            - script.execute:
+                                id: play_sound
+                                priority: true
+                                sound_file: !lambda return id(wake_word_triggered_sound);
+                            - delay: 300ms
+                      - voice_assistant.start:
+                          wake_word: !lambda return wake_word;
+
+
+
+voice_assistant:
+  id: va
+  microphone: mic0
+  media_player: nabu_media_player
+  use_wake_word: false
+  noise_suppression_level: 0
+  auto_gain: 0 dbfs
+  volume_multiplier: 1
+  on_client_connected:
+    - lambda: id(init_in_progress) = false;
+    - micro_wake_word.start:
+    - lambda: id(voice_assistant_phase) = ${voice_assist_idle_phase_id};
+    - script.execute: control_leds
+  on_client_disconnected:
+    - voice_assistant.stop:
+    - lambda: id(voice_assistant_phase) = ${voice_assist_not_ready_phase_id};
+    - script.execute: control_leds
+  on_error:
+    - if:
+        condition:
+          lambda: return !id(init_in_progress);
+        then:
+          - lambda: id(voice_assistant_phase) = ${voice_assist_error_phase_id};
+          - script.execute: control_leds
+  # When the voice assistant starts: Play a wake up sound, duck audio.
+  on_start:
+    - nabu.set_ducking:
+        decibel_reduction: 20   # Number of dB quieter; higher implies more quiet, 0 implies full volume
+        duration: 0.0s          # The duration of the transition (default is 0)
+  on_listening:
+    - lambda: id(voice_assistant_phase) = ${voice_assist_waiting_for_command_phase_id};
+    - script.execute: control_leds
+  on_stt_vad_start:
+    - lambda: id(voice_assistant_phase) = ${voice_assist_listening_for_command_phase_id};
+    - script.execute: control_leds
+  on_stt_vad_end:
+    - lambda: id(voice_assistant_phase) = ${voice_assist_thinking_phase_id};
     - script.execute: control_leds
+  on_tts_start:
+    - lambda: id(voice_assistant_phase) = ${voice_assist_replying_phase_id};
+    - script.execute: control_leds
+    # Start a script that would potentially enable the stop word if the response is longer than a second
+    - script.execute: activate_stop_word_if_tts_step_is_long
+  # When the voice assistant ends ...
+  on_end:
+    - wait_until:
+        not:
+          voice_assistant.is_running:
+    # Stop ducking audio.
+    - nabu.set_ducking:
+        decibel_reduction: 0   # 0 dB means no reduction
+        duration: 1.0s
+    # Stop the script that would potentially enable the stop word if the response is longer than a second
+    - script.stop: activate_stop_word_if_tts_step_is_long
+    # Disable the stop word (If the tiemr is not ringing)
+    - if:
+        condition:
+          switch.is_off: timer_ringing
+        then:
+          # - lambda: id(stop).disable();
+    # If the end happened because of an error, let the error phase on for a second
+    - if:
+        condition:
+          lambda: return id(voice_assistant_phase) == ${voice_assist_error_phase_id};
+        then:
+          - delay: 1s
+    # Reset the voice assistant phase id and reset the LED animations.
+    - lambda: id(voice_assistant_phase) = ${voice_assist_idle_phase_id};
+    - script.execute: control_leds
+    - micro_wake_word.start:
+  on_timer_finished:
+    - switch.turn_on: timer_ringing
+  on_timer_started:
+    - script.execute: control_leds
+  on_timer_cancelled:
+    - script.execute: control_leds
+  on_timer_updated:
+    - script.execute: control_leds
+  on_timer_tick:
+    - script.execute: control_leds
+
 
+script:
+  # Script used activate the stop word if the TTS step is long.
+  # Why is this wrapped on a script?
+  #   Becasue we want to stop the sequence if the TTS step is faster than that.
+  #   This allows us to prevent having the deactivation of the stop word before its own activation.
+  - id: activate_stop_word_if_tts_step_is_long
+    then:
+      - delay: 1s
+      # Enable stop wake word
+      # - lambda: id(stop).enable();

config/satellite_va_core_r3.yaml

@@ -75,6 +75,8 @@ packages:
   ha: !include common/home_assistant.yaml
   mp: !include common/media_player.yaml
   va: !include common/voice_assistant.yaml
+  # timer requires voice_assistant.yaml
+  timer: !include common/timer.yaml
 
   led_ring: !include 
     file: common/led_ring.yaml