diff --git a/esphome/components/i2s_audio/i2s_audio_media_player.cpp b/esphome/components/i2s_audio/i2s_audio_media_player.cpp
index 9ddc8419bf..2b624a3917 100644
--- a/esphome/components/i2s_audio/i2s_audio_media_player.cpp
+++ b/esphome/components/i2s_audio/i2s_audio_media_player.cpp
@@ -51,6 +51,22 @@ void I2SAudioMediaPlayer::control(const media_player::MediaPlayerCall &call) {
           this->state = media_player::MEDIA_PLAYER_STATE_PAUSED;
         }
         break;
+      case media_player::MEDIA_PLAYER_COMMAND_VOLUME_UP: {
+        float new_volume = this->volume + 0.1f;
+        if (new_volume > 1.0f)
+          new_volume = 1.0f;
+        this->set_volume_(new_volume);
+        this->unmute_();
+        break;
+      }
+      case media_player::MEDIA_PLAYER_COMMAND_VOLUME_DOWN: {
+        float new_volume = this->volume - 0.1f;
+        if (new_volume < 0.0f)
+          new_volume = 0.0f;
+        this->set_volume_(new_volume);
+        this->unmute_();
+        break;
+      }
     }
   }
   this->publish_state();
diff --git a/esphome/components/media_player/__init__.py b/esphome/components/media_player/__init__.py
index 98b93a7ee7..877dd693e3 100644
--- a/esphome/components/media_player/__init__.py
+++ b/esphome/components/media_player/__init__.py
@@ -29,6 +29,17 @@ PauseAction = media_player_ns.class_(
 StopAction = media_player_ns.class_(
     "StopAction", automation.Action, cg.Parented.template(MediaPlayer)
 )
+VolumeUpAction = media_player_ns.class_(
+    "VolumeUpAction", automation.Action, cg.Parented.template(MediaPlayer)
+)
+VolumeDownAction = media_player_ns.class_(
+    "VolumeDownAction", automation.Action, cg.Parented.template(MediaPlayer)
+)
+VolumeSetAction = media_player_ns.class_(
+    "VolumeSetAction", automation.Action, cg.Parented.template(MediaPlayer)
+)
+
+CONF_VOLUME = "volume"
 
 
 async def setup_media_player_core_(var, config):
@@ -45,9 +56,7 @@ async def register_media_player(var, config):
 MEDIA_PLAYER_SCHEMA = cv.ENTITY_BASE_SCHEMA.extend(cv.Schema({}))
 
 
-MEDIA_PLAYER_ACTION_SCHEMA = maybe_simple_id(
-    {cv.Required(CONF_ID): cv.use_id(MediaPlayer)}
-)
+MEDIA_PLAYER_ACTION_SCHEMA = maybe_simple_id({cv.GenerateID(): cv.use_id(MediaPlayer)})
 
 
 @automation.register_action("media_player.play", PlayAction, MEDIA_PLAYER_ACTION_SCHEMA)
@@ -58,12 +67,37 @@ MEDIA_PLAYER_ACTION_SCHEMA = maybe_simple_id(
     "media_player.pause", PauseAction, MEDIA_PLAYER_ACTION_SCHEMA
 )
 @automation.register_action("media_player.stop", StopAction, MEDIA_PLAYER_ACTION_SCHEMA)
+@automation.register_action(
+    "media_player.volume_up", VolumeUpAction, MEDIA_PLAYER_ACTION_SCHEMA
+)
+@automation.register_action(
+    "media_player.volume_down", VolumeDownAction, MEDIA_PLAYER_ACTION_SCHEMA
+)
 async def media_player_action(config, action_id, template_arg, args):
     var = cg.new_Pvariable(action_id, template_arg)
     await cg.register_parented(var, config[CONF_ID])
     return var
 
 
+@automation.register_action(
+    "media_player.volume_set",
+    VolumeSetAction,
+    cv.maybe_simple_value(
+        {
+            cv.GenerateID(): cv.use_id(MediaPlayer),
+            cv.Required(CONF_VOLUME): cv.templatable(cv.percentage),
+        },
+        key=CONF_VOLUME,
+    ),
+)
+async def media_player_volume_set_action(config, action_id, template_arg, args):
+    var = cg.new_Pvariable(action_id, template_arg)
+    await cg.register_parented(var, config[CONF_ID])
+    volume = await cg.templatable(config[CONF_VOLUME], args, float)
+    cg.add(var.set_volume(volume))
+    return var
+
+
 @coroutine_with_priority(100.0)
 async def to_code(config):
     cg.add_global(media_player_ns.using)
diff --git a/esphome/components/media_player/automation.h b/esphome/components/media_player/automation.h
index e2b40d6a00..4dc324eb9c 100644
--- a/esphome/components/media_player/automation.h
+++ b/esphome/components/media_player/automation.h
@@ -7,28 +7,23 @@ namespace esphome {
 
 namespace media_player {
 
-template<typename... Ts> class PlayAction : public Action<Ts...>, public Parented<MediaPlayer> {
-  void play(Ts... x) override {
-    this->parent_->make_call().set_command(MediaPlayerCommand::MEDIA_PLAYER_COMMAND_PLAY).perform();
-  }
-};
+#define MEDIA_PLAYER_SIMPLE_COMMAND_ACTION(ACTION_CLASS, ACTION_COMMAND) \
+  template<typename... Ts> class ACTION_CLASS : public Action<Ts...>, public Parented<MediaPlayer> { \
+    void play(Ts... x) override { \
+      this->parent_->make_call().set_command(MediaPlayerCommand::MEDIA_PLAYER_COMMAND_##ACTION_COMMAND).perform(); \
+    } \
+  };
 
-template<typename... Ts> class ToggleAction : public Action<Ts...>, public Parented<MediaPlayer> {
-  void play(Ts... x) override {
-    this->parent_->make_call().set_command(MediaPlayerCommand::MEDIA_PLAYER_COMMAND_TOGGLE).perform();
-  }
-};
+MEDIA_PLAYER_SIMPLE_COMMAND_ACTION(PlayAction, PLAY)
+MEDIA_PLAYER_SIMPLE_COMMAND_ACTION(PauseAction, PAUSE)
+MEDIA_PLAYER_SIMPLE_COMMAND_ACTION(StopAction, STOP)
+MEDIA_PLAYER_SIMPLE_COMMAND_ACTION(ToggleAction, TOGGLE)
+MEDIA_PLAYER_SIMPLE_COMMAND_ACTION(VolumeUpAction, VOLUME_UP)
+MEDIA_PLAYER_SIMPLE_COMMAND_ACTION(VolumeDownAction, VOLUME_DOWN)
 
-template<typename... Ts> class PauseAction : public Action<Ts...>, public Parented<MediaPlayer> {
-  void play(Ts... x) override {
-    this->parent_->make_call().set_command(MediaPlayerCommand::MEDIA_PLAYER_COMMAND_PAUSE).perform();
-  }
-};
-
-template<typename... Ts> class StopAction : public Action<Ts...>, public Parented<MediaPlayer> {
-  void play(Ts... x) override {
-    this->parent_->make_call().set_command(MediaPlayerCommand::MEDIA_PLAYER_COMMAND_STOP).perform();
-  }
+template<typename... Ts> class VolumeSetAction : public Action<Ts...>, public Parented<MediaPlayer> {
+  TEMPLATABLE_VALUE(float, volume)
+  void play(Ts... x) override { this->parent_->make_call().set_volume(this->volume_.value(x...)).perform(); }
 };
 
 }  // namespace media_player
diff --git a/esphome/components/media_player/media_player.h b/esphome/components/media_player/media_player.h
index 6a2643b713..88114d5337 100644
--- a/esphome/components/media_player/media_player.h
+++ b/esphome/components/media_player/media_player.h
@@ -20,7 +20,9 @@ enum MediaPlayerCommand : uint8_t {
   MEDIA_PLAYER_COMMAND_STOP = 2,
   MEDIA_PLAYER_COMMAND_MUTE = 3,
   MEDIA_PLAYER_COMMAND_UNMUTE = 4,
-  MEDIA_PLAYER_COMMAND_TOGGLE = 5
+  MEDIA_PLAYER_COMMAND_TOGGLE = 5,
+  MEDIA_PLAYER_COMMAND_VOLUME_UP = 6,
+  MEDIA_PLAYER_COMMAND_VOLUME_DOWN = 7,
 };
 const char *media_player_command_to_string(MediaPlayerCommand command);
 
diff --git a/tests/test4.yaml b/tests/test4.yaml
index ce7a87411e..6b633fbe9b 100644
--- a/tests/test4.yaml
+++ b/tests/test4.yaml
@@ -604,6 +604,14 @@ touchscreen:
       - logger.log:
           format: Touch at (%d, %d)
           args: ["touch.x", "touch.y"]
+      - media_player.play:
+      - media_player.pause:
+      - media_player.stop:
+      - media_player.toggle:
+      - media_player.volume_up:
+      - media_player.volume_down:
+      - media_player.volume_set: 50%
+
 
 media_player:
   - platform: i2s_audio