1

app.py

@@ -6,14 +6,21 @@ import numpy as np
 import tempfile
 import os
 import warnings
+import soundfile as sf
+from pydub import AudioSegment
 
 warnings.filterwarnings("ignore", category=UserWarning, module='librosa')
 
 app = FastAPI()
 
+def convert_mp3_to_wav(mp3_path, wav_path):
+    # Convert mp3 to wav using pydub and ffmpeg
+    audio = AudioSegment.from_mp3(mp3_path)
+    audio.export(wav_path, format="wav")
+
 def extract_audio_features(audio_file_path):
     # Load the audio file and extract features
-    y, sr = librosa.load(audio_file_path, sr=None)
+    y, sr = sf.read(audio_file_path)
     f0, voiced_flag, voiced_probs = librosa.pyin(y, fmin=75, fmax=600)
     f0 = f0[~np.isnan(f0)]
     energy = librosa.feature.rms(y=y)[0]
@@ -72,26 +79,31 @@ async def analyze_stress(
     # Handle audio file analysis
     if file or file_path:
         if file:
-            if not file.filename.endswith(".opus"):
-                raise HTTPException(status_code=400, detail="Only .opus files are supported.")
-            with tempfile.NamedTemporaryFile(delete=False, suffix=".opus") as temp_file:
+            if not file.filename.endswith(".mp3"):
+                raise HTTPException(status_code=400, detail="Only .mp3 files are supported.")
+            with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as temp_file:
                 temp_file.write(await file.read())
-                temp_file_path = temp_file.name
+                temp_mp3_path = temp_file.name
+                temp_wav_path = temp_mp3_path.replace(".mp3", ".wav")
+                convert_mp3_to_wav(temp_mp3_path, temp_wav_path)
         else:
-            if not file_path.endswith(".opus"):
-                raise HTTPException(status_code=400, detail="Only .opus files are supported.")
+            if not file_path.endswith(".mp3"):
+                raise HTTPException(status_code=400, detail="Only .mp3 files are supported.")
             if not os.path.exists(file_path):
                 raise HTTPException(status_code=400, detail="File path does not exist.")
-            temp_file_path = file_path
+            temp_wav_path = file_path.replace(".mp3", ".wav")
+            convert_mp3_to_wav(file_path, temp_wav_path)
 
         try:
-            result = analyze_voice_stress(temp_file_path)
+            result = analyze_voice_stress(temp_wav_path)
             return JSONResponse(content=result)
         except Exception as e:
             raise HTTPException(status_code=500, detail=str(e))
         finally:
+            # Clean up temporary files
             if file:
-                os.remove(temp_file_path)
+                os.remove(temp_mp3_path)
+                os.remove(temp_wav_path)
 
     # Handle text analysis
     elif text:

requirements.txt

@@ -1,9 +1,8 @@
 fastapi
 uvicorn
-pydantic
 librosa
 numpy
-matplotlib
-python-multipart
-
-
+pydantic
+soundfile
+pydub
+ffmpeg-python