Skip to content

Add language parameter for the audio transcription #1295

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Add language parameter for the audio transcription #1295

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
bdb644c
Add language parameter for the audio transcription
Jun 17, 2025
44b1a4b
Merge branch 'main' into feat/add-transcirption-language-param
hchmch Nov 16, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion packages/markitdown/src/markitdown/converters/_audio_converter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,10 +88,13 @@ def convert(
else:
audio_format = None

# Figure out the audio language for transcription, default to "en-US"
language = kwargs.get("language", "en-US")

# Transcribe
if audio_format:
try:
transcript = transcribe_audio(file_stream, audio_format=audio_format)
transcript = transcribe_audio(file_stream, audio_format=audio_format, language=language)
if transcript:
md_content += "\n\n### Audio Transcript:\n" + transcript
except MissingDependencyException:
Expand Down
4 changes: 2 additions & 2 deletions packages/markitdown/src/markitdown/converters/_transcribe_audio.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@
_dependency_exc_info = sys.exc_info()


def transcribe_audio(file_stream: BinaryIO, *, audio_format: str = "wav") -> str:
def transcribe_audio(file_stream: BinaryIO, *, audio_format: str = "wav", language: str = "en-US") -> str:
# Check for installed dependencies
if _dependency_exc_info is not None:
raise MissingDependencyException(
Expand All @@ -45,5 +45,5 @@ def transcribe_audio(file_stream: BinaryIO, *, audio_format: str = "wav") -> str
recognizer = sr.Recognizer()
with sr.AudioFile(audio_source) as source:
audio = recognizer.record(source)
transcript = recognizer.recognize_google(audio).strip()
transcript = recognizer.recognize_google(audio, language=language).strip()
return "[No speech detected]" if transcript == "" else transcript