diff --git a/edenai_apis/apis/faker/__init__.py b/edenai_apis/apis/faker/__init__.py
new file mode 100644
index 00000000..957c8573
--- /dev/null
+++ b/edenai_apis/apis/faker/__init__.py
@@ -0,0 +1 @@
+from .faker_api import FakerApi
diff --git a/edenai_apis/apis/faker/faker_api.py b/edenai_apis/apis/faker/faker_api.py
new file mode 100644
index 00000000..c9777950
--- /dev/null
+++ b/edenai_apis/apis/faker/faker_api.py
@@ -0,0 +1,71 @@
+"""
+    Fake provider class used for tests
+"""
+from io import BufferedReader
+from random import randint
+from time import sleep
+from typing import Dict, List, Optional
+
+from edenai_apis.features import AudioInterface, ProviderInterface
+from edenai_apis.features.audio import SpeechToTextAsyncDataClass, SpeechDiarization
+from edenai_apis.utils.types import (
+    AsyncBaseResponseType,
+    AsyncLaunchJobResponseType,
+    AsyncPendingResponseType,
+    AsyncResponseType,
+)
+
+class FakerApi(ProviderInterface, AudioInterface):
+    provider_name = "faker"
+
+    def __init__(self, api_keys: Dict = {}) -> None:
+        super().__init__()
+
+    def audio__speech_to_text_async__launch_job(
+        self, 
+        file: str,
+        language: str, 
+        speakers: int, 
+        profanity_filter: bool, 
+        vocabulary: list,
+        audio_attributes: tuple,
+        file_url: str = "",
+        provider_params: dict = dict(),
+    ) -> AsyncLaunchJobResponseType:
+        sleep(randint(1, 3))
+        return AsyncLaunchJobResponseType(provider_job_id="SomeFakeID")
+
+    def audio__speech_to_text_async__get_job_result(
+        self, provider_job_id: str
+    ) -> AsyncBaseResponseType[SpeechToTextAsyncDataClass]:
+        sleep(randint(1, 3))
+
+        standardized_response = SpeechToTextAsyncDataClass(
+                text="empty",
+                diarization=SpeechDiarization(
+                    total_speakers = 1
+                )
+            )
+        provider_correct_response = AsyncResponseType[SpeechToTextAsyncDataClass](
+                original_response={},
+                standardized_response=standardized_response,
+                provider_job_id=provider_job_id,
+            )
+
+        chance_to_stop = randint(2, 1000)
+
+        if provider_job_id == 'FINISHED':
+            return provider_correct_response
+        if provider_job_id == 'ERROR':
+            raise Exception("error")
+        if provider_job_id == "pending":
+            return AsyncPendingResponseType[SpeechToTextAsyncDataClass](
+                provider_job_id=provider_job_id
+            )
+        if chance_to_stop < 250:
+            return provider_correct_response
+        if chance_to_stop > 994:
+            raise Exception("error")
+        return AsyncPendingResponseType[SpeechToTextAsyncDataClass](
+                provider_job_id=provider_job_id
+        )
diff --git a/edenai_apis/apis/faker/info.json b/edenai_apis/apis/faker/info.json
new file mode 100644
index 00000000..0c49c4d2
--- /dev/null
+++ b/edenai_apis/apis/faker/info.json
@@ -0,0 +1,53 @@
+{
+    "audio": {
+        "speech_to_text_async": {
+            "constraints": {
+                "languages": [
+                    "ar",
+                    "bg",
+                    "ca",
+                    "hr",
+                    "cs",
+                    "da",
+                    "nl",
+                    "en",
+                    "fa",
+                    "fi",
+                    "fr",
+                    "de",
+                    "el",
+                    "he",
+                    "hi",
+                    "hu",
+                    "id",
+                    "it",
+                    "ja",
+                    "ko",
+                    "lv",
+                    "lt",
+                    "ms",
+                    "cmn",
+                    "no",
+                    "pl",
+                    "pt",
+                    "ro",
+                    "ru",
+                    "sk",
+                    "sl",
+                    "es",
+                    "sv",
+                    "ta",
+                    "te",
+                    "tr"
+                ],
+                "file_extensions": [
+                    "flac",
+                    "wav",
+                    "mp3"
+                ],
+                "allow_null_language": true
+            },
+            "version": "v1"
+        }
+    }
+}
diff --git a/edenai_apis/apis/faker/outputs/audio/speech_to_text_async_output.json b/edenai_apis/apis/faker/outputs/audio/speech_to_text_async_output.json
new file mode 100644
index 00000000..7c68e0fb
--- /dev/null
+++ b/edenai_apis/apis/faker/outputs/audio/speech_to_text_async_output.json
@@ -0,0 +1,13 @@
+{
+  "status": "succeeded",
+  "provider_job_id": "SomeFakeID",
+  "original_response": {},
+  "standardized_response": {
+    "text": "empty",
+    "diarization": {
+      "total_speakers": 1,
+      "entries": [],
+      "error_message": null
+    }
+  }
+}
\ No newline at end of file