Audio Files

# macOS
brew install exiftool

# Ubuntu/Debian
sudo apt-get install libimage-exiftool-perl

# Windows
# Download from https://exiftool.org/

pip install SpeechRecognition pydub

pip install markitdown[audio-transcription]
# or
pip install markitdown[all]

Title: Interview with Jane Doe
Artist: John Smith
Album: Tech Talks Podcast
Genre: Podcast
DateTimeOriginal: 2024:02:15 10:00:00
CreateDate: 2024:02:15 10:00:00
NumChannels: 2
SampleRate: 44100
BitsPerSample: 16

### Audio Transcript:
Welcome to today's episode. Today we're talking with Jane Doe about the future of artificial intelligence. Jane, thanks for joining us. Thanks for having me. Let's start with your background in machine learning.

### Audio Transcript:
This is a test recording. The quick brown fox jumps over the lazy dog. Testing one two three.

Title: Background Music
Artist: Various Artists
Genre: Instrumental

### Audio Transcript:
[No speech detected]

packages/markitdown/src/markitdown/converters/
├── _audio_converter.py      # Main audio converter
├── _transcribe_audio.py     # Speech transcription logic
└── _exiftool.py             # ExifTool metadata extraction

def transcribe_audio(file_stream: BinaryIO, *, audio_format: str = "wav") -> str:
    # Convert to WAV if needed
    if audio_format in ["mp3", "mp4"]:
        audio_segment = pydub.AudioSegment.from_file(file_stream, format=audio_format)
        audio_source = io.BytesIO()
        audio_segment.export(audio_source, format="wav")
        audio_source.seek(0)
    else:
        audio_source = file_stream
    
    # Transcribe with Google Speech Recognition
    recognizer = sr.Recognizer()
    with sr.AudioFile(audio_source) as source:
        audio = recognizer.record(source)
        transcript = recognizer.recognize_google(audio).strip()
        return "[No speech detected]" if transcript == "" else transcript

from markitdown import MarkItDown
import os

md = MarkItDown()
audio_dir = "recordings"

for filename in os.listdir(audio_dir):
    if filename.endswith(('.wav', '.mp3', '.m4a')):
        filepath = os.path.join(audio_dir, filename)
        print(f"Processing {filename}...")
        
        result = md.convert(filepath)
        
        # Save transcript
        output_path = filepath.replace(os.path.splitext(filepath)[1], '.md')
        with open(output_path, 'w') as f:
            f.write(result.markdown)
        
        print(f"Saved to {output_path}")

from markitdown import MarkItDown
from markitdown._exceptions import MissingDependencyException

md = MarkItDown(exiftool_path="/usr/local/bin/exiftool")

try:
    result = md.convert("music.mp3")
except MissingDependencyException:
    # Transcription not available, but metadata still extracted
    print("Transcription unavailable, showing metadata only")
    print(result.markdown)

from markitdown import MarkItDown
import re

md = MarkItDown(exiftool_path="/usr/local/bin/exiftool")
result = md.convert("podcast_episode.mp3")

# Extract title from metadata
metadata_lines = result.markdown.split('\n')
title = next((line.split(':', 1)[1].strip() for line in metadata_lines if line.startswith('Title:')), 'Unknown')

# Extract transcript
transcript_marker = '### Audio Transcript:'
if transcript_marker in result.markdown:
    transcript = result.markdown.split(transcript_marker)[1].strip()
    print(f"Episode: {title}")
    print(f"Transcript length: {len(transcript)} characters")
else:
    print("No transcript generated")

from markitdown import MarkItDown

md = MarkItDown()

# Extract and transcribe audio from video
result = md.convert("presentation.mp4")

# result.markdown contains transcription of spoken content
with open('presentation_transcript.md', 'w') as f:
    f.write(f"# Presentation Transcript\n\n{result.markdown}")

from markitdown import MarkItDown
from markitdown._exceptions import MissingDependencyException

md = MarkItDown()

try:
    result = md.convert("audio.mp3")
    print(result.markdown)
except MissingDependencyException as e:
    print("Install transcription dependencies:")
    print("pip install markitdown[audio-transcription]")
except FileNotFoundError:
    print("ffmpeg not found. Install it for MP3/M4A support:")
    print("macOS: brew install ffmpeg")
    print("Ubuntu: sudo apt-get install ffmpeg")
except Exception as e:
    print(f"Transcription failed: {e}")
    print("This may be due to:")
    print("- No speech in the audio")
    print("- Poor audio quality")
    print("- No internet connection (Google API required)")