feat: Replace pydub with ffmpeg for audio duration and metadata extraction in sound services

app/services/sound_normalizer_service.py

@@ -7,7 +7,6 @@ import re
 from pathlib import Path
 
 import ffmpeg
-from pydub import AudioSegment
 
 from app.database import db
 from app.models.sound import Sound
@@ -632,9 +631,17 @@ class SoundNormalizerService:
             # Calculate file hash
             file_hash = SoundNormalizerService._calculate_file_hash(file_path)
 
-            # Get duration using pydub
-            audio = AudioSegment.from_wav(file_path)
-            duration = len(audio)  # Duration in milliseconds
+            # Get duration using ffmpeg
+            probe = ffmpeg.probe(file_path)
+            audio_stream = next(
+                (s for s in probe['streams'] if s['codec_type'] == 'audio'),
+                None
+            )
+            
+            if audio_stream and 'duration' in audio_stream:
+                duration = int(float(audio_stream['duration']) * 1000)  # Convert to milliseconds
+            else:
+                duration = 0
 
             return {
                 "duration": duration,

app/services/sound_scanner_service.py

@@ -4,8 +4,7 @@ import hashlib
 import logging
 from pathlib import Path
 
-from pydub import AudioSegment
-from pydub.utils import mediainfo
+import ffmpeg
 
 from app.database import db
 from app.models.sound import Sound
@@ -281,32 +280,31 @@ class SoundScannerService:
 
     @staticmethod
     def _extract_audio_metadata(file_path: str) -> dict:
-        """Extract metadata from audio file using pydub and mediainfo."""
+        """Extract metadata from audio file using ffmpeg-python."""
         try:
             # Get file size
             file_size = Path(file_path).stat().st_size
 
-            # Load audio file with pydub for basic info
-            audio = AudioSegment.from_file(file_path)
+            # Use ffmpeg to probe audio metadata
+            probe = ffmpeg.probe(file_path)
+            audio_stream = next(
+                (s for s in probe['streams'] if s['codec_type'] == 'audio'),
+                None
+            )
+            
+            if not audio_stream:
+                raise ValueError("No audio stream found in file")
 
-            # Extract basic metadata from AudioSegment
-            duration = len(audio)
-            channels = audio.channels
-            sample_rate = audio.frame_rate
-
-            # Use mediainfo for more accurate bitrate information
-            bitrate = None
-            try:
-                info = mediainfo(file_path)
-                if info and "bit_rate" in info:
-                    bitrate = int(info["bit_rate"])
-                elif info and "bitrate" in info:
-                    bitrate = int(info["bitrate"])
-            except (ValueError, KeyError, TypeError):
-                # Fallback to calculated bitrate if mediainfo fails
-                if duration > 0:
-                    file_size_bits = file_size * 8
-                    bitrate = int(file_size_bits / duration / 1000)
+            # Extract metadata from ffmpeg probe
+            duration = int(float(audio_stream.get('duration', 0)) * 1000)  # Convert to milliseconds
+            channels = int(audio_stream.get('channels', 0))
+            sample_rate = int(audio_stream.get('sample_rate', 0))
+            bitrate = int(audio_stream.get('bit_rate', 0)) if audio_stream.get('bit_rate') else None
+            
+            # Fallback bitrate calculation if not available
+            if not bitrate and duration > 0:
+                file_size_bits = file_size * 8
+                bitrate = int(file_size_bits / (duration / 1000))
 
             return {
                 "duration": duration,

pyproject.toml

@@ -15,7 +15,6 @@ dependencies = [
     "flask-migrate==4.1.0",
     "flask-socketio==5.5.1",
     "flask-sqlalchemy==3.1.1",
-    "pydub==0.25.1",
     "python-dotenv==1.1.1",
     "python-vlc>=3.0.21203",
     "requests==2.32.4",

uv.lock

@@ -505,15 +505,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/13/a3/a812df4e2dd5696d1f351d58b8fe16a405b234ad2886a0dab9183fb78109/pycparser-2.22-py3-none-any.whl", hash = "sha256:c3702b6d3dd8c7abc1afa565d7e63d53a1d0bd86cdc24edd75470f4de499cfcc", size = 117552 },
 ]
 
-[[package]]
-name = "pydub"
-version = "0.25.1"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/fe/9a/e6bca0eed82db26562c73b5076539a4a08d3cffd19c3cc5913a3e61145fd/pydub-0.25.1.tar.gz", hash = "sha256:980a33ce9949cab2a569606b65674d748ecbca4f0796887fd6f46173a7b0d30f", size = 38326 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/a6/53/d78dc063216e62fc55f6b2eebb447f6a4b0a59f55c8406376f76bf959b08/pydub-0.25.1-py2.py3-none-any.whl", hash = "sha256:65617e33033874b59d87db603aa1ed450633288aefead953b30bded59cb599a6", size = 32327 },
-]
-
 [[package]]
 name = "pygments"
 version = "2.19.2"
@@ -645,7 +636,6 @@ dependencies = [
     { name = "flask-migrate" },
     { name = "flask-socketio" },
     { name = "flask-sqlalchemy" },
-    { name = "pydub" },
     { name = "python-dotenv" },
     { name = "python-vlc" },
     { name = "requests" },
@@ -671,7 +661,6 @@ requires-dist = [
     { name = "flask-migrate", specifier = "==4.1.0" },
     { name = "flask-socketio", specifier = "==5.5.1" },
     { name = "flask-sqlalchemy", specifier = "==3.1.1" },
-    { name = "pydub", specifier = "==0.25.1" },
     { name = "python-dotenv", specifier = "==1.1.1" },
     { name = "python-vlc", specifier = ">=3.0.21203" },
     { name = "requests", specifier = "==2.32.4" },