use one pipeline media player

Author: Kevin Ahrendt

esp32-s3-box-3/esp32-s3-box-3.yaml

@@ -64,11 +64,6 @@ psram:
   mode: octal
   speed: 80MHz
 
-external_components:
-  - source: github://jesserockz/esphome-components
-    components: [file]
-    refresh: 0s
-
 api:
   on_client_connected:
     - script.execute: draw_display
@@ -150,7 +145,7 @@ audio_dac:
   - platform: es8311
     id: es8311_dac
     bits_per_sample: 16bit
-    sample_rate: 16000
+    sample_rate: 48000
 
 microphone:
   - platform: i2s_audio
@@ -165,11 +160,35 @@ speaker:
     id: box_speaker
     i2s_dout_pin: GPIO15
     dac_type: external
-    sample_rate: 16000
+    sample_rate: 48000
     bits_per_sample: 16bit
     channel: left
     audio_dac: es8311_dac
-    buffer_duration: 1000ms  # The timer finished audio needs to fit entirely in the buffer
+    buffer_duration: 100ms
+
+media_player:
+  - platform: speaker
+    name: Media Player
+    id: speaker_media_player
+    announcement_pipeline:
+      speaker: box_speaker
+      format: FLAC
+      sample_rate: 48000
+      num_channels: 1  # S3 Box only has one output channel
+    files:
+      - id: timer_finished_sound
+        file: https://github.com/esphome/home-assistant-voice-pe/raw/dev/sounds/timer_finished.flac
+    on_announcement:
+      - if:
+          condition:
+            lambda: return id(voice_assistant_phase) == ${voice_assist_idle_phase_id};
+          then:
+            - script.execute: stop_voice_assistant
+            - lambda: id(voice_assistant_phase) = ${voice_assist_muted_phase_id};
+            - script.execute: draw_display
+    on_idle:
+      - script.execute: start_voice_assistant
+      - script.execute: draw_display
 
 micro_wake_word:
   models:
@@ -181,7 +200,7 @@ micro_wake_word:
 voice_assistant:
   id: va
   microphone: box_mic
-  speaker: box_speaker
+  media_player: speaker_media_player
   noise_suppression_level: 2
   auto_gain: 31dBFS
   volume_multiplier: 2.0
@@ -206,10 +225,12 @@ voice_assistant:
     - text_sensor.template.publish:
         id: text_response
         state: !lambda return x;
-  on_tts_stream_start:
     - lambda: id(voice_assistant_phase) = ${voice_assist_replying_phase_id};
     - script.execute: draw_display
-  on_tts_stream_end:
+  on_end:
+    - wait_until:
+        not:
+          media_player.is_announcing:
     - if:
         condition:
           switch.is_off: mute
@@ -218,10 +239,6 @@ voice_assistant:
         else:
           - lambda: id(voice_assistant_phase) = ${voice_assist_muted_phase_id};
     - script.execute: draw_display
-  on_end:
-    - wait_until:
-        not:
-          voice_assistant.is_running:
     - if:
         condition:
           and:
@@ -252,6 +269,7 @@ voice_assistant:
     - script.execute: draw_display
   on_client_disconnected:
     - script.execute: stop_voice_assistant
+    - lambda: id(voice_assistant_phase) = ${voice_assist_not_ready_phase_id};
     - script.execute: draw_display
   on_timer_started:
     - script.execute: draw_display
@@ -262,29 +280,10 @@ voice_assistant:
   on_timer_tick:
     - script.execute: draw_display
   on_timer_finished:
-    - script.execute: stop_voice_assistant
-    - lambda: id(voice_assistant_phase) = ${voice_assist_timer_finished_phase_id};
     - switch.turn_on: timer_ringing
-    - script.execute: draw_display
-    - wait_until:
-        not:
-          microphone.is_capturing:
-    - while:
-        condition:
-          switch.is_on: timer_ringing
-        then:
-          # Ensure the speaker starts before trying to send the timer finished audio
-          - lambda: id(box_speaker).start();
-          - wait_until:
-              condition:
-                speaker.is_playing:
-          - lambda: id(box_speaker).play(id(timer_finished_wave_file), sizeof(id(timer_finished_wave_file)));
-          - delay: 1s
     - wait_until:
-        not:
-          speaker.is_playing:
-    - switch.turn_off: timer_ringing
-    - script.execute: start_voice_assistant
+        media_player.is_announcing:
+    - lambda: id(voice_assistant_phase) = ${voice_assist_timer_finished_phase_id};
     - script.execute: draw_display
 
 script:
@@ -472,7 +471,6 @@ script:
           then:
             - voice_assistant.stop:
             - micro_wake_word.stop:
-      - lambda: id(voice_assistant_phase) = ${voice_assist_not_ready_phase_id};
 
 switch:
   - platform: gpio
@@ -528,7 +526,30 @@ switch:
     optimistic: true
     internal: true
     restore_mode: ALWAYS_OFF
+    on_turn_off:
+      # Turn off the repeat mode and disable the pause between playlist items
+      - 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);
+      # Stop playing the alarm
+      - media_player.stop:
+          announcement: true
     on_turn_on:
+      # Turn on the repeat mode and pause for 1000 ms between playlist items/repeats
+      - 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
 
@@ -705,10 +726,6 @@ color:
   - id: paused_timer_color
     hex: "3b89e3"
 
-file:
-  - id: timer_finished_wave_file
-    file: https://github.com/esphome/wake-word-voice-assistants/raw/main/sounds/timer_finished.wav
-
 spi:
   - id: spi_bus
     clk_pin: 7