diff --git a/esphome/components/camera_encoder/__init__.py b/esphome/components/camera_encoder/__init__.py
index c0f0ca2fe0..89181d27b4 100644
--- a/esphome/components/camera_encoder/__init__.py
+++ b/esphome/components/camera_encoder/__init__.py
@@ -2,7 +2,6 @@ import esphome.codegen as cg
 from esphome.components.esp32 import add_idf_component
 import esphome.config_validation as cv
 from esphome.const import CONF_BUFFER_SIZE, CONF_ID, CONF_TYPE
-from esphome.core import CORE
 from esphome.types import ConfigType
 
 CODEOWNERS = ["@DT-art1"]
@@ -51,9 +50,8 @@ async def to_code(config: ConfigType) -> None:
     buffer = cg.new_Pvariable(config[CONF_ENCODER_BUFFER_ID])
     cg.add(buffer.set_buffer_size(config[CONF_BUFFER_SIZE]))
     if config[CONF_TYPE] == ESP32_CAMERA_ENCODER:
-        if CORE.using_esp_idf:
-            add_idf_component(name="espressif/esp32-camera", ref="2.1.0")
-        cg.add_build_flag("-DUSE_ESP32_CAMERA_JPEG_ENCODER")
+        add_idf_component(name="espressif/esp32-camera", ref="2.1.1")
+        cg.add_define("USE_ESP32_CAMERA_JPEG_ENCODER")
         var = cg.new_Pvariable(
             config[CONF_ID],
             config[CONF_QUALITY],
diff --git a/esphome/components/camera_encoder/esp32_camera_jpeg_encoder.cpp b/esphome/components/camera_encoder/esp32_camera_jpeg_encoder.cpp
index 7e21122087..55a3f0b96c 100644
--- a/esphome/components/camera_encoder/esp32_camera_jpeg_encoder.cpp
+++ b/esphome/components/camera_encoder/esp32_camera_jpeg_encoder.cpp
@@ -1,3 +1,5 @@
+#include "esphome/core/defines.h"
+
 #ifdef USE_ESP32_CAMERA_JPEG_ENCODER
 
 #include "esp32_camera_jpeg_encoder.h"
@@ -15,7 +17,7 @@ camera::EncoderError ESP32CameraJPEGEncoder::encode_pixels(camera::CameraImageSp
   this->bytes_written_ = 0;
   this->out_of_output_memory_ = false;
   bool success = fmt2jpg_cb(pixels->get_data_buffer(), pixels->get_data_length(), spec->width, spec->height,
-                            to_internal_(spec->format), this->quality_, callback_, this);
+                            to_internal_(spec->format), this->quality_, callback, this);
 
   if (!success)
     return camera::ENCODER_ERROR_CONFIGURATION;
@@ -49,7 +51,7 @@ void ESP32CameraJPEGEncoder::dump_config() {
                 this->output_->get_max_size(), this->quality_, this->buffer_expand_size_);
 }
 
-size_t ESP32CameraJPEGEncoder::callback_(void *arg, size_t index, const void *data, size_t len) {
+size_t ESP32CameraJPEGEncoder::callback(void *arg, size_t index, const void *data, size_t len) {
   ESP32CameraJPEGEncoder *that = reinterpret_cast<ESP32CameraJPEGEncoder *>(arg);
   uint8_t *buffer = that->output_->get_data();
   size_t buffer_length = that->output_->get_max_size();
diff --git a/esphome/components/camera_encoder/esp32_camera_jpeg_encoder.h b/esphome/components/camera_encoder/esp32_camera_jpeg_encoder.h
index b585252584..0ede366e73 100644
--- a/esphome/components/camera_encoder/esp32_camera_jpeg_encoder.h
+++ b/esphome/components/camera_encoder/esp32_camera_jpeg_encoder.h
@@ -1,5 +1,7 @@
 #pragma once
 
+#include "esphome/core/defines.h"
+
 #ifdef USE_ESP32_CAMERA_JPEG_ENCODER
 
 #include <esp_camera.h>
@@ -24,7 +26,7 @@ class ESP32CameraJPEGEncoder : public camera::Encoder {
   void dump_config() override;
   // -------------------------
  protected:
-  static size_t callback_(void *arg, size_t index, const void *data, size_t len);
+  static size_t callback(void *arg, size_t index, const void *data, size_t len);
   pixformat_t to_internal_(camera::PixelFormat format);
 
   camera::EncoderBuffer *output_{};
diff --git a/esphome/core/defines.h b/esphome/core/defines.h
index bdc59598f6..784e8cd2b3 100644
--- a/esphome/core/defines.h
+++ b/esphome/core/defines.h
@@ -157,6 +157,7 @@
 #define USE_ESP32_BLE_SERVER
 #define USE_ESP32_BLE_UUID
 #define USE_ESP32_BLE_ADVERTISING
+#define USE_ESP32_CAMERA_JPEG_ENCODER
 #define USE_I2C
 #define USE_IMPROV
 #define USE_MICROPHONE