Update app.py

app.py

@@ -1,22 +1,24 @@
 import os
 import gradio as gr
-import elevenlabs
-from elevenlabs.client import ElevenLabs
-from speech_recognition import Recognizer, AudioFile
+#import elevenlabs
+#from elevenlabs.client import ElevenLabs
+#from speech_recognition import Recognizer, AudioFile
 import io
 from google import genai
 from google.genai import types
-from dotenv import load_dotenv
-from elevenlabs import play
+#from dotenv import load_dotenv
+#from elevenlabs import play
+from TTS.api import TTS
 
-load_dotenv()
-
-elevenlabs = ElevenLabs(
-  api_key=os.getenv("ELEVENLABS_API_KEY"),
-)
+#load_dotenv()
 
+#elevenlabs = ElevenLabs(
+#  api_key=os.getenv("ELEVENLABS_API_KEY"),
+#)
 
 
+# --- TTS Setup ---
+tts = TTS(model_name="tts_models/multilingual/multi-dataset/xtts_v2", progress_bar=False, gpu=False)
 
 # --- API Keys (Set as environment variables for security!) ---
 genai_api_key = os.environ.get("GOOGLE_API_KEY")  # Gemini API Key
@@ -28,7 +30,7 @@ genai_api_key = os.environ.get("GOOGLE_API_KEY")  # Gemini API Key
 client = genai.Client(api_key=genai_api_key)
 
 # --- ElevenLabs Voice ---
-voice = "Bella"  # Choose a voice from ElevenLabs
+voice = "p225"#"Bella"  # Choose a voice from ElevenLabs
 
 # --- Language Tutor Parameters ---
 target_language = "Arabic"
@@ -70,15 +72,18 @@ def evaluate_answer(question, answer):
 def text_to_speech(text, voice):
     """Converts text to speech using ElevenLabs."""
 
-    audio = elevenlabs.text_to_speech.convert(
-    text=text,
-    voice_id="JBFqnCBsd6RMkjVDRZzb",
-    model_id="eleven_monolingual_v1",
+    #audio = elevenlabs.text_to_speech.convert(
+    #text=text,
+    #voice_id="JBFqnCBsd6RMkjVDRZzb",
+    #model_id="eleven_monolingual_v1",
     #output_format="mp3_44100_128",
     )
     
     #audio = elevenlabs.tts(text=text, voice=voice, model="eleven_monolingual_v1")
-    return b"".join(audio)
+    #return b"".join(audio)
+    wav = tts.tts(text=text, speaker=voice, language=target_language, speed=1.0)
+    return wav
+
 
 def transcribe_audio(audio_file):
     """Transcribes audio using SpeechRecognition."""
@@ -111,7 +116,7 @@ def process_answer(audio_file, question, question_audio):
 
 # --- Gradio Interface ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Adaptive Language Tutor (Spanish)")
+    gr.Markdown("# Adaptive Language Tutor (Arabic)")
     with gr.Row():
         generate_button = gr.Button("Generate Question")
         question_audio_output = gr.Audio(label="Question")