diff --git a/src/frontends/tensorflow_common/include/common_op_table.hpp b/src/frontends/tensorflow_common/include/common_op_table.hpp
index 9d32aa0f780..08bf463807a 100644
--- a/src/frontends/tensorflow_common/include/common_op_table.hpp
+++ b/src/frontends/tensorflow_common/include/common_op_table.hpp
@@ -84,6 +84,7 @@ OP_CONVERTER(translate_gather_op);
 OP_CONVERTER(translate_gather_v2_op);
 OP_CONVERTER(translate_gather_nd_op);
 OP_CONVERTER(translate_gather_tree_op);
+OP_CONVERTER(translate_gelu_op);
 OP_CONVERTER(translate_identity_op);
 OP_CONVERTER(translate_identity_n_op);
 OP_CONVERTER(translate_ifft_op);
diff --git a/src/frontends/tensorflow_common/src/op/gelu.cpp b/src/frontends/tensorflow_common/src/op/gelu.cpp
new file mode 100644
index 00000000000..7ae644f0f44
--- /dev/null
+++ b/src/frontends/tensorflow_common/src/op/gelu.cpp
@@ -0,0 +1,31 @@
+// Copyright (C) 2024 Intel Corporation
+// SPDX-License-Identifier: Apache-2.0
+//
+
+#include "openvino/op/gelu.hpp"
+
+#include "common_op_table.hpp"
+
+using namespace std;
+using namespace ov;
+using namespace ov::op;
+
+namespace ov {
+namespace frontend {
+namespace tensorflow {
+namespace op {
+
+OutputVector translate_gelu_op(const NodeContext& node) {
+    default_op_checks(node, 1, {"GELU"});
+    auto input = node.get_input(0);
+    auto approximate = node.get_attribute<bool>("approximate");
+    const auto mode = (approximate == true) ? ov::op::GeluApproximationMode::TANH : ov::op::GeluApproximationMode::ERF;
+    auto res = make_shared<ov::op::v7::Gelu>(input, mode);
+    set_node_name(node.get_name(), res);
+    return res->outputs();
+};
+
+}  // namespace op
+}  // namespace tensorflow
+}  // namespace frontend
+}  // namespace ov
diff --git a/src/frontends/tensorflow_lite/src/op/gelu.cpp b/src/frontends/tensorflow_lite/src/op/gelu.cpp
new file mode 100644
index 00000000000..3ded6cc8082
--- /dev/null
+++ b/src/frontends/tensorflow_lite/src/op/gelu.cpp
@@ -0,0 +1,27 @@
+// Copyright (C) 2024 Intel Corporation
+// SPDX-License-Identifier: Apache-2.0
+//
+
+#include "common_op_table.hpp"
+#include "op_translation_utils.hpp"
+#include "utils.hpp"
+
+using namespace std;
+
+namespace ov {
+namespace frontend {
+namespace tensorflow_lite {
+namespace op {
+
+OutputVector gelu(const ov::frontend::tensorflow_lite::NodeContext& node) {
+    const auto& decoder = get_decoder(node);
+    std::map<std::string, ov::Any> attrs{
+        {"approximate", decoder->get_attribute(&tflite::GeluOptions::approximate)},
+    };
+    return attribute_helper(node, attrs, ov::frontend::tensorflow::op::translate_gelu_op);
+}
+
+}  // namespace op
+}  // namespace tensorflow_lite
+}  // namespace frontend
+}  // namespace ov
diff --git a/src/frontends/tensorflow_lite/src/op_table.cpp b/src/frontends/tensorflow_lite/src/op_table.cpp
index aab01caff2b..f85d5dcb708 100644
--- a/src/frontends/tensorflow_lite/src/op_table.cpp
+++ b/src/frontends/tensorflow_lite/src/op_table.cpp
@@ -86,7 +86,7 @@ std::map<std::string, CreatorFunction> get_supported_ops() {
         {"FULLY_CONNECTED", DEQUANTIZE_INPUTS(fully_connected)},
         {"GATHER", DEQUANTIZE_INPUTS(gather)},
         {"GATHER_ND", DEQUANTIZE_INPUTS(translate_gather_nd_op)},
-        // GELU
+        {"GELU", DEQUANTIZE_INPUTS(gelu)},
         {"GREATER", translate_binary<opset8::Greater>},
         {"GREATER_EQUAL", translate_binary<opset8::GreaterEqual>},
         {"HARD_SWISH", translate_unary<opset8::HSwish>},
diff --git a/src/frontends/tensorflow_lite/src/op_table.hpp b/src/frontends/tensorflow_lite/src/op_table.hpp
index 385d200dff0..637f39ad827 100644
--- a/src/frontends/tensorflow_lite/src/op_table.hpp
+++ b/src/frontends/tensorflow_lite/src/op_table.hpp
@@ -39,6 +39,7 @@ TFL_OP_CONVERTER(depthwise_conv2d);
 TFL_OP_CONVERTER(dequantize);
 TFL_OP_CONVERTER(fully_connected);
 TFL_OP_CONVERTER(gather);
+TFL_OP_CONVERTER(gelu);
 TFL_OP_CONVERTER(l2_normalization);
 TFL_OP_CONVERTER(leaky_relu);
 TFL_OP_CONVERTER(max_pool_2d);
diff --git a/tests/layer_tests/tensorflow2_keras_tests/test_tf2_keras_activation.py b/tests/layer_tests/tensorflow2_keras_tests/test_tf2_keras_activation.py
index a5756b248f1..2d8ecaf6f19 100644
--- a/tests/layer_tests/tensorflow2_keras_tests/test_tf2_keras_activation.py
+++ b/tests/layer_tests/tensorflow2_keras_tests/test_tf2_keras_activation.py
@@ -14,6 +14,7 @@ class TestKerasActivation(CommonTF2LayerTest):
             # pytest-xdist can't execute the tests in parallel because workers can't compare tests scopes before run
             # tf.nn.<activation> operation have no "==" operation to be compared
             "elu": tf.nn.elu,
+            "gelu": tf.nn.gelu,
             "relu": tf.nn.relu,
             "sigmoid": tf.nn.sigmoid,
             "softmax": tf.nn.softmax,
@@ -40,6 +41,8 @@ class TestKerasActivation(CommonTF2LayerTest):
     test_data_float32 = [
         dict(activation_func="elu", input_names=["x1"], input_shapes=[[5, 4]],
              input_type=tf.float32),
+        dict(activation_func="gelu", input_names=["x1"], input_shapes=[[5, 4]],
+             input_type=tf.float32),
         dict(activation_func="relu", input_names=["x1"], input_shapes=[[5, 4, 8]],
              input_type=tf.float32),
         dict(activation_func="sigmoid", input_names=["x1"], input_shapes=[[5, 4, 8, 3]],