diff --git a/docs/articles_en/documentation/openvino_ir/operation_sets/available_opsets/opset13.md b/docs/articles_en/documentation/openvino_ir/operation_sets/available_opsets/opset13.md
index 8f016a0dadd..32c024c3356 100644
--- a/docs/articles_en/documentation/openvino_ir/operation_sets/available_opsets/opset13.md
+++ b/docs/articles_en/documentation/openvino_ir/operation_sets/available_opsets/opset13.md
@@ -73,6 +73,7 @@ Table of Contents
 * :doc:`ExperimentalDetectronTopKROIs_6 <openvino_docs_ops_sort_ExperimentalDetectronTopKROIs_6>`
 * :doc:`ExtractImagePatches <openvino_docs_ops_movement_ExtractImagePatches_3>`
 * :doc:`Eye <openvino_docs_ops_generation_Eye_9>`
+* :doc:`FakeConvert <openvino_docs_ops_quantization_FakeConvert_13>`
 * :doc:`FakeQuantize <openvino_docs_ops_quantization_FakeQuantize_1>`
 * :doc:`Floor <openvino_docs_ops_arithmetic_Floor_1>`
 * :doc:`FloorMod <openvino_docs_ops_arithmetic_FloorMod_1>`
diff --git a/docs/articles_en/documentation/openvino_ir/operation_sets/operations_specifications.md b/docs/articles_en/documentation/openvino_ir/operation_sets/operations_specifications.md
index b26b57022d7..10d97deddd8 100644
--- a/docs/articles_en/documentation/openvino_ir/operation_sets/operations_specifications.md
+++ b/docs/articles_en/documentation/openvino_ir/operation_sets/operations_specifications.md
@@ -68,6 +68,7 @@
    ExperimentalDetectronTopKROIs-6 <openvino_docs_ops_sort_ExperimentalDetectronTopKROIs_6>
    ExtractImagePatches-3 <openvino_docs_ops_movement_ExtractImagePatches_3>
    Eye-9 <openvino_docs_ops_generation_Eye_9>
+   FakeConvert-13 <openvino_docs_ops_quantization_FakeConvert_13>
    FakeQuantize-1 <openvino_docs_ops_quantization_FakeQuantize_1>
    FloorMod-1 <openvino_docs_ops_arithmetic_FloorMod_1>
    Floor-1 <openvino_docs_ops_arithmetic_Floor_1>
diff --git a/docs/articles_en/documentation/openvino_ir/operation_sets/operations_specifications/quantization/FakeConvert_13.md b/docs/articles_en/documentation/openvino_ir/operation_sets/operations_specifications/quantization/FakeConvert_13.md
new file mode 100644
index 00000000000..1d060460202
--- /dev/null
+++ b/docs/articles_en/documentation/openvino_ir/operation_sets/operations_specifications/quantization/FakeConvert_13.md
@@ -0,0 +1,98 @@
+# FakeConvert {#openvino_docs_ops_quantization_FakeConvert_13}
+
+**Note**: FakeConvert is an experimental operation and subject to change.
+
+@sphinxdirective
+
+.. meta::
+  :description: Learn about FakeConvert-13 - a quantization operation.
+
+**Versioned name**: *FakeConvert-13*
+
+**Category**: *Quantization*
+
+**Short description**: *FakeConvert* is element-wise quantization of floating-point input values into a set of values corresponding to a target low-precision floating-point type.
+
+**Detailed description**: *FakeConvert* operation converts the input tensor to a specified target low-precision floating-point type and performs backward conversion to the source precision. It also applies affine transformation defined by ``scale`` and ``shift`` parameters before the conversion step and its reverse form after the backward conversion.
+
+It emulates types defined by the ``destination_type`` attribute, on the original type of the ``data`` input.
+
+Possible destination types are: "f8e4m3", "f8e5m2". The "f8e4m3" is an 8-bit floating-point format, where 1 bit for the sign, 4 bits for the exponents and 3 bits for the mantissa. The "f8e5m2" is an 8-bit floating-point format, where 1 bit is for the sign, 5 bits for the exponents and 2 for the mantissa.
+The FP8 types were introduced in the following paper: `FP8 Formats for Deep Learning <https://arxiv.org/abs/2209.05433>`__ .
+
+*Fake* in *FakeConvert* means that the output tensor preserve the same element type as an original type of the input tensor, not the ``destination_type``.
+
+Each element of the output is defined as the result of the following expression:
+
+.. code-block:: py
+   :force:
+
+    data = (data + shift) / scale
+    ConvertLike(Convert(data, destination_type), data)
+    data = data * scale - shift
+
+
+**Attributes**
+
+* *destination_type*
+
+  * **Description**: *destination_type* is the emulated type
+  * **Range of values**: "f8e4m3", "f8e5m2"
+  * **Type**: `string`
+  * **Required**: *yes*
+
+
+**Inputs**:
+
+* **1**: `data` - tensor of type *T_F* and arbitrary shape. **Required.**
+* **2**: `scale` - tensor of type *T_F* with a scale factor for the *data* input value. The shape must be numpy-broadcastable to the shape of *data*. **Required.**
+* **3**: `shift` - tensor of type *T_F* with value to subtract before and add after conversion of the *data* input value. The shape must be numpy-broadcastable to the shape of *data*, and match the shape of the *scale* input. **Optional.**
+
+
+**Outputs**:
+
+* **1**: Output tensor of type *T_F* with shape and type matching the 1st input tensor *data*.
+
+**Types**
+
+* *T_F*: supported floating-point type (`FP16`, `BF16`, `FP32`).
+
+**Example**
+
+.. code-block:: xml
+   :force:
+
+   <layer … type="FakeConvert"…>
+       <data destination_type="f8e4m3"/>
+       <input>
+           <port id="0">
+               <dim>1</dim>
+               <dim>64</dim>
+               <dim>56</dim>
+               <dim>56</dim>
+           </port>
+           <port id="1">
+               <dim>1</dim>
+               <dim>64</dim>
+               <dim>1</dim>
+               <dim>1</dim>
+           </port>
+           <port id="2">
+               <dim>1</dim>
+               <dim>64</dim>
+               <dim>1</dim>
+               <dim>1</dim>
+           </port>
+       </input>
+       <output>
+           <port id="3">
+               <dim>1</dim>
+               <dim>64</dim>
+               <dim>56</dim>
+               <dim>56</dim>
+           </port>
+       </output>
+   </layer>
+
+
+@endsphinxdirective