diff --git a/.dockerignore b/.dockerignore
new file mode 100644
index 0000000..f59ec20
--- /dev/null
+++ b/.dockerignore
@@ -0,0 +1 @@
+*
\ No newline at end of file
diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..d2f31ef
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1 @@
+tests/test_files/** linguist-vendored
diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..492ad8a
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,16 @@
+FROM python:3.13-alpine
+
+USER root
+
+# Runtime dependency
+RUN apk add --no-cache ffmpeg
+
+RUN pip install markitdown
+
+# Default USERID and GROUPID
+ARG USERID=10000
+ARG GROUPID=10000
+
+USER $USERID:$GROUPID
+
+ENTRYPOINT [ "markitdown" ]
diff --git a/README.md b/README.md
index dba35b6..8aa5e2a 100644
--- a/README.md
+++ b/README.md
@@ -59,7 +59,8 @@ You can pipe content to standard input by omitting the argument:
 cat path-to-file.pdf | markitdown
 ```
 
-You can also configure markitdown to use Large Language Models to describe images. To do so you must provide llm_client and llm_model parameters to MarkItDown object, according to your specific client.
+You can also configure markitdown to use Large Language Models to describe images. To do so you must provide `llm_client` and `llm_model` parameters to MarkItDown object, according to your specific client.
+
 
 ```python
 from markitdown import MarkItDown
@@ -71,6 +72,13 @@ result = md.convert("example.jpg")
 print(result.text_content)
 ```
 
+You can also use the project as Docker Image:
+
+```sh
+docker build -t markitdown:latest .
+docker run --rm -i markitdown:latest < ~/your-file.pdf > output.md
+```
+
 ## Contributing
 
 This project welcomes contributions and suggestions.  Most contributions require you to agree to a
diff --git a/src/markitdown/_markitdown.py b/src/markitdown/_markitdown.py
index 4ee1990..cfbb243 100644
--- a/src/markitdown/_markitdown.py
+++ b/src/markitdown/_markitdown.py
@@ -15,6 +15,7 @@ import traceback
 import zipfile
 from typing import Any, Dict, List, Optional, Union
 from urllib.parse import parse_qs, quote, unquote, urlparse, urlunparse
+from warnings import catch_warnings
 
 import mammoth
 import markdownify
@@ -31,7 +32,13 @@ from charset_normalizer import from_path
 
 # Optional Transcription support
 try:
-    import pydub
+    # Using warnings' catch_warnings to catch
+    # pydub's warning of ffmpeg or avconv missing
+    with catch_warnings(record=True) as w:
+        import pydub
+
+        if w:
+            raise ModuleNotFoundError
     import speech_recognition as sr
 
     IS_AUDIO_TRANSCRIPTION_CAPABLE = True
@@ -344,8 +351,11 @@ class YouTubeConverter(DocumentConverter):
                 assert isinstance(params["v"][0], str)
                 video_id = str(params["v"][0])
                 try:
+                    youtube_transcript_languages = kwargs.get(
+                        "youtube_transcript_languages", ("en",)
+                    )
                     # Must be a single transcript.
-                    transcript = YouTubeTranscriptApi.get_transcript(video_id)  # type: ignore
+                    transcript = YouTubeTranscriptApi.get_transcript(video_id, languages=youtube_transcript_languages)  # type: ignore
                     transcript_text = " ".join([part["text"] for part in transcript])  # type: ignore
                     # Alternative formatting:
                     # formatter = TextFormatter()
@@ -1153,7 +1163,7 @@ class MarkItDown:
                 self._append_ext(extensions, g)
 
             # Convert
-            result = self._convert(temp_path, extensions, url=response.url)
+            result = self._convert(temp_path, extensions, url=response.url, **kwargs)
         # Clean up
         finally:
             try: