diff --git a/libs/langchain/langchain/document_loaders/audio.py b/libs/langchain/langchain/document_loaders/audio.py
index 4fe4985a6b788..db35165daa729 100644
--- a/libs/langchain/langchain/document_loaders/audio.py
+++ b/libs/langchain/langchain/document_loaders/audio.py
@@ -1,27 +1,24 @@
-from typing import Any, Iterator, List
+from __future__ import annotations
 
-from langchain_core.documents.base import Document
+from pathlib import Path
+from typing import Any, Union
 
-from langchain.document_loaders import Blob
-from langchain.document_loaders.base import BaseLoader
+from langchain.document_loaders.blob_loaders import FileSystemBlobLoader
+from langchain.document_loaders.generic import GenericLoader
 from langchain.document_loaders.parsers.audio import AzureSpeechServiceParser
 
 
-class AzureSpeechServiceLoader(BaseLoader):
-    def __init__(self, file_path: str, **kwargs: Any) -> None:
-        """Initialize with file path."""
-        super().__init__()
-
-        self.file_path = file_path
-        self.parser = AzureSpeechServiceParser(**kwargs)
-
-    def load(self) -> List[Document]:
-        """Eagerly load the content."""
-        return list(self.lazy_load())
-
-    def lazy_load(
-        self,
-    ) -> Iterator[Document]:
-        """Lazily lod documents."""
-        blob = Blob.from_path(self.file_path)
-        return iter(self.parser.parse(blob))
+class AzureSpeechServiceLoader(GenericLoader):
+    @classmethod
+    def from_path(
+        cls, path: Union[str, Path], **kwargs: Any
+    ) -> AzureSpeechServiceLoader:
+        path = path if isinstance(path, Path) else Path(path)
+        if path.is_file():
+            loader_params: dict = {"glob": path.name}
+            path = path.parent
+        else:
+            loader_params = {}
+        loader = FileSystemBlobLoader(path, **loader_params)
+        parser = AzureSpeechServiceParser(**kwargs)
+        return cls(loader, parser)
diff --git a/libs/langchain/langchain/document_loaders/blob_loaders/schema.py b/libs/langchain/langchain/document_loaders/blob_loaders/schema.py
index 9d1e737e3745a..b9bfaa4aff992 100644
--- a/libs/langchain/langchain/document_loaders/blob_loaders/schema.py
+++ b/libs/langchain/langchain/document_loaders/blob_loaders/schema.py
@@ -155,9 +155,7 @@ class BlobLoader(ABC):
     """
 
     @abstractmethod
-    def yield_blobs(
-        self,
-    ) -> Iterable[Blob]:
+    def yield_blobs(self) -> Iterable[Blob]:
         """A lazy loader for raw data represented by LangChain's Blob object.
 
         Returns:
diff --git a/libs/langchain/langchain/document_loaders/parsers/audio.py b/libs/langchain/langchain/document_loaders/parsers/audio.py
index 3c73a8eb312f7..f14f5e64d6142 100644
--- a/libs/langchain/langchain/document_loaders/parsers/audio.py
+++ b/libs/langchain/langchain/document_loaders/parsers/audio.py
@@ -346,11 +346,9 @@ def lazy_parse(self, blob: Blob) -> Iterator[Document]:
         except ImportError:
             raise ImportError(
                 "azure.cognitiveservices.speech package not found, please install "
-                "it with `pip install azure-cognitiveservices-speech`"
+                "it with `pip install azure-cognitiveservices-speech`."
             )
 
-        """transcribes a conversation"""
-
         def conversation_transcriber_recognition_canceled_cb(
             evt: speechsdk.SessionEventArgs
         ) -> None:
diff --git a/libs/langchain/tests/unit_tests/document_loaders/test_audio.py b/libs/langchain/tests/integration_tests/test_audio.py
similarity index 78%
rename from libs/langchain/tests/unit_tests/document_loaders/test_audio.py
rename to libs/langchain/tests/integration_tests/test_audio.py
index b09f117eaf547..f4b23d7291671 100644
--- a/libs/langchain/tests/unit_tests/document_loaders/test_audio.py
+++ b/libs/langchain/tests/integration_tests/test_audio.py
@@ -15,7 +15,7 @@ def _get_csv_file_path() -> str:
 
 
 def test_azure_speech_load_key_region_auto_detect_languages() -> None:
-    loader = AzureSpeechServiceLoader(
+    loader = AzureSpeechServiceLoader.from_path(
         _get_csv_file_path(),
         key=SPEECH_SERVICE_KEY,
         region=SPEECH_SERVICE_REGION,
@@ -26,7 +26,7 @@ def test_azure_speech_load_key_region_auto_detect_languages() -> None:
 
 
 def test_azure_speech_load_key_region_language() -> None:
-    loader = AzureSpeechServiceLoader(
+    loader = AzureSpeechServiceLoader.from_path(
         _get_csv_file_path(),
         key=SPEECH_SERVICE_KEY,
         region=SPEECH_SERVICE_REGION,
@@ -37,7 +37,7 @@ def test_azure_speech_load_key_region_language() -> None:
 
 
 def test_azure_speech_load_key_region() -> None:
-    loader = AzureSpeechServiceLoader(
+    loader = AzureSpeechServiceLoader.from_path(
         _get_csv_file_path(), key=SPEECH_SERVICE_KEY, region=SPEECH_SERVICE_REGION
     )
     documents = loader.load()
@@ -45,10 +45,13 @@ def test_azure_speech_load_key_region() -> None:
 
 
 def test_azure_speech_load_key_endpoint() -> None:
-    loader = AzureSpeechServiceLoader(
+    loader = AzureSpeechServiceLoader.from_path(
         _get_csv_file_path(),
         key=SPEECH_SERVICE_KEY,
-        endpoint=f"wss://{SPEECH_SERVICE_REGION}.stt.speech.microsoft.com/speech/recognition/conversation/cognitiveservices/v1",
+        endpoint=(
+            f"wss://{SPEECH_SERVICE_REGION}.stt.speech.microsoft.com/speech/recognition"
+            "/conversation/cognitiveservices/v1",
+        ),
     )
     documents = loader.load()
     assert "what" in documents[0].page_content.lower()
diff --git a/libs/langchain/tests/unit_tests/document_loaders/test_audio/whatstheweatherlike.wav b/libs/langchain/tests/integration_tests/test_audio/whatstheweatherlike.wav
similarity index 100%
rename from libs/langchain/tests/unit_tests/document_loaders/test_audio/whatstheweatherlike.wav
rename to libs/langchain/tests/integration_tests/test_audio/whatstheweatherlike.wav
diff --git a/libs/langchain/tests/unit_tests/document_loaders/test_audio.png b/libs/langchain/tests/unit_tests/document_loaders/test_audio.png
deleted file mode 100644
index 2c05c29d811fe..0000000000000
Binary files a/libs/langchain/tests/unit_tests/document_loaders/test_audio.png and /dev/null differ