diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index 0e94df76..584450d9 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -7,7 +7,7 @@ on:
   workflow_dispatch:
   pull_request:
   schedule:
-    - cron: '0 5 * * 1'
+    - cron: "0 5 * * 1"
 
 concurrency:
   # yamllint disable-line rule:line-length
@@ -38,6 +38,9 @@ jobs:
             device: pico-w
           - firmware: voice-assistant
             device: m5stack-atom-echo
+          - firmware: voice-assistant
+            device: esp32-s3-box
+            version: dev
 
     steps:
       - uses: actions/checkout@v4
@@ -86,7 +89,6 @@ jobs:
           name: ${{ matrix.project }}
           path: manifest.json
 
-
   full-manifests:
     name: Create ${{ matrix.project }} manifest
     runs-on: ubuntu-latest
diff --git a/voice-assistant/esp32-s3-box.yaml b/voice-assistant/esp32-s3-box.yaml
new file mode 100644
index 00000000..cfb1986c
--- /dev/null
+++ b/voice-assistant/esp32-s3-box.yaml
@@ -0,0 +1,117 @@
+esphome:
+  name: esp32-s3-box
+  friendly_name: ESP32 S3 Box
+  platformio_options:
+    board_build.flash_mode: dio
+
+  on_boot:
+    - priority: -100
+      then:
+        - wait_until: api.connected
+        - delay: 1s
+        - voice_assistant.start_continuous:
+  project:
+    name: esphome.esp32-s3-box-voice-assistant
+    version: "1.0"
+  min_version: "2023.9.0-dev"
+
+esp32:
+  board: esp32s3box
+  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"
+
+wifi:
+  ap:
+
+api:
+ota:
+logger:
+  hardware_uart: USB_SERIAL_JTAG
+
+binary_sensor:
+  - platform: gpio
+    pin:
+      number: GPIO1
+      inverted: true
+    name: "Mute"
+
+  - platform: gpio
+    pin:
+      number: GPIO0
+      mode: INPUT_PULLUP
+      inverted: true
+    name: Top Left Button
+    disabled_by_default: true
+    on_click:
+      - if:
+          condition: voice_assistant.is_running
+          then:
+            - voice_assistant.stop:
+          else:
+            - voice_assistant.start_continuous:
+
+output:
+  - platform: ledc
+    pin: GPIO45
+    id: backlight_output
+
+light:
+  - platform: monochromatic
+    output: backlight_output
+    name: LCD Backlight
+    id: backlight
+    restore_mode: ALWAYS_OFF
+    disabled_by_default: true
+    default_transition_length: 0s
+    effects:
+      - pulse:
+          transition_length: 250ms
+          update_interval: 250ms
+
+microphone:
+  - platform: esp_adf
+    id: box_mic
+
+speaker:
+  - platform: esp_adf
+    id: box_speaker
+
+voice_assistant:
+  microphone: box_mic
+  use_wake_word: true
+  speaker: box_speaker
+  on_start:
+    - light.turn_on:
+        id: backlight
+        brightness: 100%
+  on_tts_end:
+    - light.turn_on:
+        id: backlight
+        brightness: 100%
+  on_end:
+    - delay: 100ms
+    - wait_until:
+        not:
+          speaker.is_playing:
+    - light.turn_off: backlight
+  on_error:
+    - light.turn_off:
+        id: backlight
+
+external_components:
+  - source: github://pr#5230
+    components: esp_adf
+    refresh: 0s
+  - source: github://pr#5229
+    components:
+      - voice_assistant
+      - api
+    refresh: 0s
+
+psram:
+  mode: octal
+  speed: 80MHz