diff --git a/esphome/components/i2s_audio/__init__.py b/esphome/components/i2s_audio/__init__.py
index 05e44696d8..90dc8a24ee 100644
--- a/esphome/components/i2s_audio/__init__.py
+++ b/esphome/components/i2s_audio/__init__.py
@@ -1,16 +1,16 @@
-import esphome.config_validation as cv
-import esphome.final_validate as fv
-import esphome.codegen as cg
-
 from esphome import pins
-from esphome.const import CONF_ID
+import esphome.codegen as cg
 from esphome.components.esp32 import get_esp32_variant
 from esphome.components.esp32.const import (
     VARIANT_ESP32,
+    VARIANT_ESP32C3,
     VARIANT_ESP32S2,
     VARIANT_ESP32S3,
-    VARIANT_ESP32C3,
 )
+import esphome.config_validation as cv
+from esphome.const import CONF_CHANNEL, CONF_ID, CONF_SAMPLE_RATE
+from esphome.cpp_generator import MockObjClass
+import esphome.final_validate as fv
 
 CODEOWNERS = ["@jesserockz"]
 DEPENDENCIES = ["esp32"]
@@ -25,16 +25,22 @@ CONF_I2S_LRCLK_PIN = "i2s_lrclk_pin"
 CONF_I2S_AUDIO = "i2s_audio"
 CONF_I2S_AUDIO_ID = "i2s_audio_id"
 
+CONF_BITS_PER_SAMPLE = "bits_per_sample"
 CONF_I2S_MODE = "i2s_mode"
 CONF_PRIMARY = "primary"
 CONF_SECONDARY = "secondary"
 
+CONF_LEFT = "left"
+CONF_RIGHT = "right"
+CONF_STEREO = "stereo"
+
 i2s_audio_ns = cg.esphome_ns.namespace("i2s_audio")
 I2SAudioComponent = i2s_audio_ns.class_("I2SAudioComponent", cg.Component)
-I2SAudioIn = i2s_audio_ns.class_("I2SAudioIn", cg.Parented.template(I2SAudioComponent))
-I2SAudioOut = i2s_audio_ns.class_(
-    "I2SAudioOut", cg.Parented.template(I2SAudioComponent)
+I2SAudioBase = i2s_audio_ns.class_(
+    "I2SAudioBase", cg.Parented.template(I2SAudioComponent)
 )
+I2SAudioIn = i2s_audio_ns.class_("I2SAudioIn", I2SAudioBase)
+I2SAudioOut = i2s_audio_ns.class_("I2SAudioOut", I2SAudioBase)
 
 i2s_mode_t = cg.global_ns.enum("i2s_mode_t")
 I2S_MODE_OPTIONS = {
@@ -50,6 +56,59 @@ I2S_PORTS = {
     VARIANT_ESP32C3: 1,
 }
 
+i2s_channel_fmt_t = cg.global_ns.enum("i2s_channel_fmt_t")
+I2S_CHANNELS = {
+    CONF_LEFT: i2s_channel_fmt_t.I2S_CHANNEL_FMT_ONLY_LEFT,
+    CONF_RIGHT: i2s_channel_fmt_t.I2S_CHANNEL_FMT_ONLY_RIGHT,
+    CONF_STEREO: i2s_channel_fmt_t.I2S_CHANNEL_FMT_RIGHT_LEFT,
+}
+
+i2s_bits_per_sample_t = cg.global_ns.enum("i2s_bits_per_sample_t")
+I2S_BITS_PER_SAMPLE = {
+    8: i2s_bits_per_sample_t.I2S_BITS_PER_SAMPLE_8BIT,
+    16: i2s_bits_per_sample_t.I2S_BITS_PER_SAMPLE_16BIT,
+    32: i2s_bits_per_sample_t.I2S_BITS_PER_SAMPLE_32BIT,
+}
+
+INTERNAL_ADC_VARIANTS = [VARIANT_ESP32]
+PDM_VARIANTS = [VARIANT_ESP32, VARIANT_ESP32S3]
+
+_validate_bits = cv.float_with_unit("bits", "bit")
+
+
+def i2s_audio_component_schema(
+    class_: MockObjClass,
+    default_sample_rate: int,
+    default_channel: str,
+    default_bits_per_sample: str,
+):
+    return cv.Schema(
+        {
+            cv.GenerateID(): cv.declare_id(class_),
+            cv.GenerateID(CONF_I2S_AUDIO_ID): cv.use_id(I2SAudioComponent),
+            cv.Optional(CONF_CHANNEL, default=default_channel): cv.enum(I2S_CHANNELS),
+            cv.Optional(CONF_SAMPLE_RATE, default=default_sample_rate): cv.int_range(
+                min=1
+            ),
+            cv.Optional(CONF_BITS_PER_SAMPLE, default=default_bits_per_sample): cv.All(
+                _validate_bits, cv.enum(I2S_BITS_PER_SAMPLE)
+            ),
+            cv.Optional(CONF_I2S_MODE, default=CONF_PRIMARY): cv.enum(
+                I2S_MODE_OPTIONS, lower=True
+            ),
+        }
+    )
+
+
+async def register_i2s_audio_component(var, config):
+    await cg.register_parented(var, config[CONF_I2S_AUDIO_ID])
+
+    cg.add(var.set_i2s_mode(config[CONF_I2S_MODE]))
+    cg.add(var.set_channel(config[CONF_CHANNEL]))
+    cg.add(var.set_sample_rate(config[CONF_SAMPLE_RATE]))
+    cg.add(var.set_bits_per_sample(config[CONF_BITS_PER_SAMPLE]))
+
+
 CONFIG_SCHEMA = cv.Schema(
     {
         cv.GenerateID(): cv.declare_id(I2SAudioComponent),
diff --git a/esphome/components/i2s_audio/i2s_audio.h b/esphome/components/i2s_audio/i2s_audio.h
index d8d4a23dde..727fb6c4e1 100644
--- a/esphome/components/i2s_audio/i2s_audio.h
+++ b/esphome/components/i2s_audio/i2s_audio.h
@@ -11,9 +11,23 @@ namespace i2s_audio {
 
 class I2SAudioComponent;
 
-class I2SAudioIn : public Parented<I2SAudioComponent> {};
+class I2SAudioBase : public Parented<I2SAudioComponent> {
+ public:
+  void set_i2s_mode(i2s_mode_t mode) { this->i2s_mode_ = mode; }
+  void set_channel(i2s_channel_fmt_t channel) { this->channel_ = channel; }
+  void set_sample_rate(uint32_t sample_rate) { this->sample_rate_ = sample_rate; }
+  void set_bits_per_sample(i2s_bits_per_sample_t bits_per_sample) { this->bits_per_sample_ = bits_per_sample; }
 
-class I2SAudioOut : public Parented<I2SAudioComponent> {};
+ protected:
+  i2s_mode_t i2s_mode_{};
+  i2s_channel_fmt_t channel_;
+  uint32_t sample_rate_;
+  i2s_bits_per_sample_t bits_per_sample_;
+};
+
+class I2SAudioIn : public I2SAudioBase {};
+
+class I2SAudioOut : public I2SAudioBase {};
 
 class I2SAudioComponent : public Component {
  public:
diff --git a/esphome/components/i2s_audio/microphone/__init__.py b/esphome/components/i2s_audio/microphone/__init__.py
index 844f176bea..e2ece03e68 100644
--- a/esphome/components/i2s_audio/microphone/__init__.py
+++ b/esphome/components/i2s_audio/microphone/__init__.py
@@ -1,20 +1,19 @@
-import esphome.config_validation as cv
-import esphome.codegen as cg
-
 from esphome import pins
-from esphome.const import CONF_CHANNEL, CONF_ID, CONF_NUMBER, CONF_SAMPLE_RATE
-from esphome.components import microphone, esp32
+import esphome.codegen as cg
+from esphome.components import esp32, microphone
 from esphome.components.adc import ESP32_VARIANT_ADC1_PIN_TO_CHANNEL, validate_adc_pin
+import esphome.config_validation as cv
+from esphome.const import CONF_ID, CONF_NUMBER
 
 from .. import (
-    CONF_I2S_MODE,
-    CONF_PRIMARY,
-    I2S_MODE_OPTIONS,
-    i2s_audio_ns,
-    I2SAudioComponent,
-    I2SAudioIn,
-    CONF_I2S_AUDIO_ID,
     CONF_I2S_DIN_PIN,
+    CONF_RIGHT,
+    INTERNAL_ADC_VARIANTS,
+    PDM_VARIANTS,
+    I2SAudioIn,
+    i2s_audio_component_schema,
+    i2s_audio_ns,
+    register_i2s_audio_component,
 )
 
 CODEOWNERS = ["@jesserockz"]
@@ -23,29 +22,13 @@ DEPENDENCIES = ["i2s_audio"]
 CONF_ADC_PIN = "adc_pin"
 CONF_ADC_TYPE = "adc_type"
 CONF_PDM = "pdm"
-CONF_BITS_PER_SAMPLE = "bits_per_sample"
+
 CONF_USE_APLL = "use_apll"
 
 I2SAudioMicrophone = i2s_audio_ns.class_(
     "I2SAudioMicrophone", I2SAudioIn, microphone.Microphone, cg.Component
 )
 
-i2s_channel_fmt_t = cg.global_ns.enum("i2s_channel_fmt_t")
-CHANNELS = {
-    "left": i2s_channel_fmt_t.I2S_CHANNEL_FMT_ONLY_LEFT,
-    "right": i2s_channel_fmt_t.I2S_CHANNEL_FMT_ONLY_RIGHT,
-}
-i2s_bits_per_sample_t = cg.global_ns.enum("i2s_bits_per_sample_t")
-BITS_PER_SAMPLE = {
-    16: i2s_bits_per_sample_t.I2S_BITS_PER_SAMPLE_16BIT,
-    32: i2s_bits_per_sample_t.I2S_BITS_PER_SAMPLE_32BIT,
-}
-
-INTERNAL_ADC_VARIANTS = [esp32.const.VARIANT_ESP32]
-PDM_VARIANTS = [esp32.const.VARIANT_ESP32, esp32.const.VARIANT_ESP32S3]
-
-_validate_bits = cv.float_with_unit("bits", "bit")
-
 
 def validate_esp32_variant(config):
     variant = esp32.get_esp32_variant()
@@ -62,19 +45,7 @@ def validate_esp32_variant(config):
 
 
 BASE_SCHEMA = microphone.MICROPHONE_SCHEMA.extend(
-    {
-        cv.GenerateID(): cv.declare_id(I2SAudioMicrophone),
-        cv.GenerateID(CONF_I2S_AUDIO_ID): cv.use_id(I2SAudioComponent),
-        cv.Optional(CONF_CHANNEL, default="right"): cv.enum(CHANNELS),
-        cv.Optional(CONF_SAMPLE_RATE, default=16000): cv.int_range(min=1),
-        cv.Optional(CONF_BITS_PER_SAMPLE, default="32bit"): cv.All(
-            _validate_bits, cv.enum(BITS_PER_SAMPLE)
-        ),
-        cv.Optional(CONF_USE_APLL, default=False): cv.boolean,
-        cv.Optional(CONF_I2S_MODE, default=CONF_PRIMARY): cv.enum(
-            I2S_MODE_OPTIONS, lower=True
-        ),
-    }
+    i2s_audio_component_schema(I2SAudioMicrophone, 16000, CONF_RIGHT, "32bit")
 ).extend(cv.COMPONENT_SCHEMA)
 
 CONFIG_SCHEMA = cv.All(
@@ -89,6 +60,7 @@ CONFIG_SCHEMA = cv.All(
                 {
                     cv.Required(CONF_I2S_DIN_PIN): pins.internal_gpio_input_pin_number,
                     cv.Required(CONF_PDM): cv.boolean,
+                    cv.Optional(CONF_USE_APLL, default=False): cv.boolean,
                 }
             ),
         },
@@ -101,8 +73,8 @@ CONFIG_SCHEMA = cv.All(
 async def to_code(config):
     var = cg.new_Pvariable(config[CONF_ID])
     await cg.register_component(var, config)
-
-    await cg.register_parented(var, config[CONF_I2S_AUDIO_ID])
+    await register_i2s_audio_component(var, config)
+    await microphone.register_microphone(var, config)
 
     if config[CONF_ADC_TYPE] == "internal":
         variant = esp32.get_esp32_variant()
@@ -112,11 +84,4 @@ async def to_code(config):
     else:
         cg.add(var.set_din_pin(config[CONF_I2S_DIN_PIN]))
         cg.add(var.set_pdm(config[CONF_PDM]))
-
-    cg.add(var.set_i2s_mode(config[CONF_I2S_MODE]))
-    cg.add(var.set_channel(config[CONF_CHANNEL]))
-    cg.add(var.set_sample_rate(config[CONF_SAMPLE_RATE]))
-    cg.add(var.set_bits_per_sample(config[CONF_BITS_PER_SAMPLE]))
-    cg.add(var.set_use_apll(config[CONF_USE_APLL]))
-
-    await microphone.register_microphone(var, config)
+        cg.add(var.set_use_apll(config[CONF_USE_APLL]))
diff --git a/esphome/components/i2s_audio/microphone/i2s_audio_microphone.h b/esphome/components/i2s_audio/microphone/i2s_audio_microphone.h
index 07ca0528aa..56fb4c252a 100644
--- a/esphome/components/i2s_audio/microphone/i2s_audio_microphone.h
+++ b/esphome/components/i2s_audio/microphone/i2s_audio_microphone.h
@@ -30,11 +30,6 @@ class I2SAudioMicrophone : public I2SAudioIn, public microphone::Microphone, pub
   }
 #endif
 
-  void set_i2s_mode(i2s_mode_t mode) { this->i2s_mode_ = mode; }
-
-  void set_channel(i2s_channel_fmt_t channel) { this->channel_ = channel; }
-  void set_sample_rate(uint32_t sample_rate) { this->sample_rate_ = sample_rate; }
-  void set_bits_per_sample(i2s_bits_per_sample_t bits_per_sample) { this->bits_per_sample_ = bits_per_sample; }
   void set_use_apll(uint32_t use_apll) { this->use_apll_ = use_apll; }
 
  protected:
@@ -48,10 +43,7 @@ class I2SAudioMicrophone : public I2SAudioIn, public microphone::Microphone, pub
   bool adc_{false};
 #endif
   bool pdm_{false};
-  i2s_mode_t i2s_mode_{};
-  i2s_channel_fmt_t channel_;
-  uint32_t sample_rate_;
-  i2s_bits_per_sample_t bits_per_sample_;
+
   bool use_apll_;
 
   HighFrequencyLoopRequester high_freq_;
diff --git a/esphome/components/i2s_audio/speaker/__init__.py b/esphome/components/i2s_audio/speaker/__init__.py
index 72455af1b7..11fdae0436 100644
--- a/esphome/components/i2s_audio/speaker/__init__.py
+++ b/esphome/components/i2s_audio/speaker/__init__.py
@@ -1,15 +1,18 @@
-import esphome.codegen as cg
-import esphome.config_validation as cv
 from esphome import pins
-from esphome.const import CONF_ID, CONF_MODE
+import esphome.codegen as cg
 from esphome.components import esp32, speaker
+import esphome.config_validation as cv
+from esphome.const import CONF_CHANNEL, CONF_ID
 
 from .. import (
-    CONF_I2S_AUDIO_ID,
     CONF_I2S_DOUT_PIN,
-    I2SAudioComponent,
+    CONF_LEFT,
+    CONF_RIGHT,
+    CONF_STEREO,
     I2SAudioOut,
+    i2s_audio_component_schema,
     i2s_audio_ns,
+    register_i2s_audio_component,
 )
 
 CODEOWNERS = ["@jesserockz"]
@@ -19,18 +22,16 @@ I2SAudioSpeaker = i2s_audio_ns.class_(
     "I2SAudioSpeaker", cg.Component, speaker.Speaker, I2SAudioOut
 )
 
-i2s_dac_mode_t = cg.global_ns.enum("i2s_dac_mode_t")
 
-CONF_MUTE_PIN = "mute_pin"
 CONF_DAC_TYPE = "dac_type"
 
+i2s_dac_mode_t = cg.global_ns.enum("i2s_dac_mode_t")
 INTERNAL_DAC_OPTIONS = {
-    "left": i2s_dac_mode_t.I2S_DAC_CHANNEL_LEFT_EN,
-    "right": i2s_dac_mode_t.I2S_DAC_CHANNEL_RIGHT_EN,
-    "stereo": i2s_dac_mode_t.I2S_DAC_CHANNEL_BOTH_EN,
+    CONF_LEFT: i2s_dac_mode_t.I2S_DAC_CHANNEL_LEFT_EN,
+    CONF_RIGHT: i2s_dac_mode_t.I2S_DAC_CHANNEL_RIGHT_EN,
+    CONF_STEREO: i2s_dac_mode_t.I2S_DAC_CHANNEL_BOTH_EN,
 }
 
-EXTERNAL_DAC_OPTIONS = ["mono", "stereo"]
 
 NO_INTERNAL_DAC_VARIANTS = [esp32.const.VARIANT_ESP32S2]
 
@@ -44,28 +45,21 @@ def validate_esp32_variant(config):
     return config
 
 
+BASE_SCHEMA = speaker.SPEAKER_SCHEMA.extend(
+    i2s_audio_component_schema(I2SAudioSpeaker, 16000, "stereo", "16bit")
+).extend(cv.COMPONENT_SCHEMA)
+
 CONFIG_SCHEMA = cv.All(
     cv.typed_schema(
         {
-            "internal": speaker.SPEAKER_SCHEMA.extend(
+            "internal": BASE_SCHEMA,
+            "external": BASE_SCHEMA.extend(
                 {
-                    cv.GenerateID(): cv.declare_id(I2SAudioSpeaker),
-                    cv.GenerateID(CONF_I2S_AUDIO_ID): cv.use_id(I2SAudioComponent),
-                    cv.Required(CONF_MODE): cv.enum(INTERNAL_DAC_OPTIONS, lower=True),
-                }
-            ).extend(cv.COMPONENT_SCHEMA),
-            "external": speaker.SPEAKER_SCHEMA.extend(
-                {
-                    cv.GenerateID(): cv.declare_id(I2SAudioSpeaker),
-                    cv.GenerateID(CONF_I2S_AUDIO_ID): cv.use_id(I2SAudioComponent),
                     cv.Required(
                         CONF_I2S_DOUT_PIN
                     ): pins.internal_gpio_output_pin_number,
-                    cv.Optional(CONF_MODE, default="mono"): cv.one_of(
-                        *EXTERNAL_DAC_OPTIONS, lower=True
-                    ),
                 }
-            ).extend(cv.COMPONENT_SCHEMA),
+            ),
         },
         key=CONF_DAC_TYPE,
     ),
@@ -76,12 +70,10 @@ CONFIG_SCHEMA = cv.All(
 async def to_code(config):
     var = cg.new_Pvariable(config[CONF_ID])
     await cg.register_component(var, config)
+    await register_i2s_audio_component(var, config)
     await speaker.register_speaker(var, config)
 
-    await cg.register_parented(var, config[CONF_I2S_AUDIO_ID])
-
     if config[CONF_DAC_TYPE] == "internal":
-        cg.add(var.set_internal_dac_mode(config[CONF_MODE]))
+        cg.add(var.set_internal_dac_mode(config[CONF_CHANNEL]))
     else:
         cg.add(var.set_dout_pin(config[CONF_I2S_DOUT_PIN]))
-        cg.add(var.set_external_dac_channels(2 if config[CONF_MODE] == "stereo" else 1))
diff --git a/esphome/components/i2s_audio/speaker/i2s_audio_speaker.cpp b/esphome/components/i2s_audio/speaker/i2s_audio_speaker.cpp
index cf5a2c2766..ab26edd8cf 100644
--- a/esphome/components/i2s_audio/speaker/i2s_audio_speaker.cpp
+++ b/esphome/components/i2s_audio/speaker/i2s_audio_speaker.cpp
@@ -64,17 +64,17 @@ void I2SAudioSpeaker::player_task(void *params) {
   xQueueSend(this_speaker->event_queue_, &event, portMAX_DELAY);
 
   i2s_driver_config_t config = {
-      .mode = (i2s_mode_t) (I2S_MODE_MASTER | I2S_MODE_TX),
-      .sample_rate = 16000,
-      .bits_per_sample = I2S_BITS_PER_SAMPLE_16BIT,
-      .channel_format = I2S_CHANNEL_FMT_RIGHT_LEFT,
+      .mode = (i2s_mode_t) (this_speaker->i2s_mode_ | I2S_MODE_TX),
+      .sample_rate = this_speaker->sample_rate_,
+      .bits_per_sample = this_speaker->bits_per_sample_,
+      .channel_format = this_speaker->channel_,
       .communication_format = I2S_COMM_FORMAT_STAND_I2S,
       .intr_alloc_flags = ESP_INTR_FLAG_LEVEL1,
       .dma_buf_count = 8,
       .dma_buf_len = 128,
       .use_apll = false,
       .tx_desc_auto_clear = true,
-      .fixed_mclk = I2S_PIN_NO_CHANGE,
+      .fixed_mclk = 0,
       .mclk_multiple = I2S_MCLK_MULTIPLE_256,
       .bits_per_chan = I2S_BITS_PER_CHAN_DEFAULT,
   };
diff --git a/esphome/components/i2s_audio/speaker/i2s_audio_speaker.h b/esphome/components/i2s_audio/speaker/i2s_audio_speaker.h
index 0bdb67ceba..8d602e1ead 100644
--- a/esphome/components/i2s_audio/speaker/i2s_audio_speaker.h
+++ b/esphome/components/i2s_audio/speaker/i2s_audio_speaker.h
@@ -38,7 +38,7 @@ struct DataEvent {
   uint8_t data[BUFFER_SIZE];
 };
 
-class I2SAudioSpeaker : public Component, public speaker::Speaker, public I2SAudioOut {
+class I2SAudioSpeaker : public I2SAudioOut, public speaker::Speaker, public Component {
  public:
   float get_setup_priority() const override { return esphome::setup_priority::LATE; }
 
@@ -49,7 +49,6 @@ class I2SAudioSpeaker : public Component, public speaker::Speaker, public I2SAud
 #if SOC_I2S_SUPPORTS_DAC
   void set_internal_dac_mode(i2s_dac_mode_t mode) { this->internal_dac_mode_ = mode; }
 #endif
-  void set_external_dac_channels(uint8_t channels) { this->external_dac_channels_ = channels; }
 
   void start() override;
   void stop() override;
@@ -76,7 +75,6 @@ class I2SAudioSpeaker : public Component, public speaker::Speaker, public I2SAud
 #if SOC_I2S_SUPPORTS_DAC
   i2s_dac_mode_t internal_dac_mode_{I2S_DAC_CHANNEL_DISABLE};
 #endif
-  uint8_t external_dac_channels_;
 };
 
 }  // namespace i2s_audio