changed audio

app.py

@@ -4,7 +4,8 @@ import torch
 import gradio as gr
 from PIL import Image
 from TTS.api import TTS
-from playsound import playsound
+from pydub import AudioSegment
+from pydub.playback import play
 import os
 import random
 
@@ -164,14 +165,14 @@ def get_emotion_image(emotion):
 def generate_speech(text, emotion="happy"):
     """Generate speech from text using Coqui TTS."""
 
-    output_path = os.path.join(OUTPUT_DIR, "response.wav")
-    model_name = "tts_models/ja/kokoro/tacotron2-DDC"  # Adjust based on preferred voice
-    
-    tts = TTS(model_name=model_name, progress_bar=False, gpu=True)
-    
     output_path = "output/response.wav"
+
+    # Ensure output directory exists
+    os.makedirs(os.path.dirname(output_path), exist_ok=True)
+
+    # Generate speech file
     tts.tts_to_file(text=text, file_path=output_path)
-    
+
     return output_path
 
 @spaces.GPU
@@ -262,7 +263,8 @@ Rena:"""
     tts_audio = generate_speech(response, emotion=current_emotion)
 
     # Play audio on the local system (for testing)
-    playsound(tts_audio)  
+    audio = AudioSegment.from_file(tts_audio, format="wav")
+    play(audio) 
 
     # Add Rena's response to the conversation history
     conversation_history.append(f"Rena: {response}")

setup.sh

@@ -1,19 +1,2 @@
-apt-get update
 #!/bin/bash -e
-
-apt-get update
-
-apt-get install -y \
-    gobject-introspection \
-    libgirepository1.0-dev \
-    gir1.2-gtk-3.0 \
-    python3-gi \
-    python3-gi-cairo \
-    libcairo2-dev \
-    libglib2.0-dev \
-    libgirepository1.0-dev \
-    pkg-config \
-    cmake \
-    build-essential \
-    meson \
-    ninja-build
+apt-get update && apt-get install -y ffmpeg