Update app.py

app.py

@@ -1,73 +1,68 @@
+import spaces
 import gradio as gr
-import pyttsx3
-import speech_recognition as sr
-from gtts import gTTS
+import edge_tts
+import asyncio
+import tempfile
 import os
 
-# Initialize Text-to-Speech engine (pyttsx3 for offline or gTTS for better quality)
-engine = pyttsx3.init()
+# Get all available voices
+async def get_voices():
+    voices = await edge_tts.list_voices()
+    return {f"{v['ShortName']} - {v['Locale']} ({v['Gender']})": v['ShortName'] for v in voices}
 
-# Initialize Speech Recognition engine
-recognizer = sr.Recognizer()
+# Text-to-speech function
+async def text_to_speech(text, voice, rate, pitch):
+    if not text.strip():
+        return None, gr.Warning("Please enter text to convert.")
+    if not voice:
+        return None, gr.Warning("Please select a voice.")
+    
+    voice_short_name = voice.split(" - ")[0]
+    rate_str = f"{rate:+d}%"
+    pitch_str = f"{pitch:+d}Hz"
+    communicate = edge_tts.Communicate(text, voice_short_name, rate=rate_str, pitch=pitch_str)
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp_file:
+        tmp_path = tmp_file.name
+        await communicate.save(tmp_path)
+    return tmp_path, None
 
-# Define Menu items for the restaurant
-menu = {
-    "pizza": "Delicious pepperoni pizza with cheese and sauce.",
-    "burger": "Beef burger with lettuce, tomato, and cheese.",
-    "pasta": "Creamy pasta with garlic and parmesan.",
-    "salad": "A healthy vegetable salad with olive oil dressing."
-}
+# Gradio interface function
+@spaces.GPU
+def tts_interface(text, voice, rate, pitch):
+    audio, warning = asyncio.run(text_to_speech(text, voice, rate, pitch))
+    return audio, warning
 
-# Function to convert text to speech using gTTS
-def speak_response(text):
-    tts = gTTS(text=text, lang='en')
-    tts.save("response.mp3")
-    os.system("start response.mp3")  # Windows; on Linux, use 'mpg321 response.mp3'
-
-# Function to listen to user speech and convert it to text
-def listen_input():
-    with sr.Microphone() as source:
-        print("Listening for order...")
-        audio = recognizer.listen(source)
-        try:
-            command = recognizer.recognize_google(audio)
-            print(f"You said: {command}")
-            return command
-        except sr.UnknownValueError:
-            return "Sorry, I didn't understand that. Could you please repeat?"
-        except sr.RequestError:
-            return "Sorry, there was an issue with the speech service."
-
-# Function to handle menu interaction and confirm orders
-def handle_order(item):
-    item = item.lower()
-    response = menu.get(item, "Sorry, we don't have that item on the menu.")
-    speak_response(response)
-    return response
-
-# Gradio interface setup
-def chatbot_interface():
-    with gr.Blocks() as demo:
-        # Display menu logo image (optional)
-        gr.Image("assets/menu_logo.png", label="Click to speak", elem_id="voice_logo", interactive=True)
-
-        # Textbox for displaying responses
-        output_text = gr.Textbox(label="Assistant Response", interactive=False)
-
-        # Microphone button to listen to user input
-        audio_input = gr.Audio(source="microphone", type="numpy", label="Speak your order")
-
-        # Handle audio input and provide the appropriate response
-        def on_audio_input(audio):
-            user_input = listen_input()  # Convert speech to text
-            response = handle_order(user_input)  # Handle order
-            output_text.update(value=response)  # Display assistant's response
-            return response
-
-        # Attach microphone action to trigger audio input
-        audio_input.change(on_audio_input, inputs=[audio_input], outputs=[output_text])
+# Create Gradio application
+import gradio as gr
 
-    demo.launch()
+async def create_demo():
+    voices = await get_voices()
+    
+    description = """
+    Experience the power of Voicecloning.be for text-to-speech conversion.
+    """
+    
+    demo = gr.Interface(
+        fn=tts_interface,
+        inputs=[
+            gr.Textbox(label="Input Text", lines=5),
+            gr.Dropdown(choices=[""] + list(voices.keys()), label="Select Voice", value=""),
+            gr.Slider(minimum=-50, maximum=50, value=0, label="Speech Rate Adjustment (%)", step=1),
+            gr.Slider(minimum=-20, maximum=20, value=0, label="Pitch Adjustment (Hz)", step=1)
+        ],
+        outputs=[
+            gr.Audio(label="Generated Audio", type="filepath"),
+            gr.Markdown(label="Warning", visible=False)
+        ],
+        title="Voicecloning.be Text-to-Speech",
+        description=description,
+        article="Experience the power of Voicecloning.be for text-to-speech conversion.",
+        analytics_enabled=False,
+        allow_flagging=False
+    )
+    return demo
 
+# Run the application
 if __name__ == "__main__":
-    chatbot_interface()
+    demo = asyncio.run(create_demo())
+    demo.launch()