Update app.py

app.py

@@ -1,53 +1,48 @@
 import gradio as gr
 from TTS.api import TTS
-import os 
 
-os.system("pip uninstall -y gradio")
-os.system("pip install gradio==2.6.4")
+# Initialize TTS models
+tts = TTS(model_name="tts_models/multilingual/multi-dataset/your_tts", progress_bar=False, gpu=False)
 
-# Initialize the Text-to-Speech models
-tts_engine = TTS(model_name="tts_models/multilingual/multi-dataset/your_tts", progress_bar=False, gpu=False)
-
-# Function to convert text to speech
-def convert_text_to_speech(input_text: str, audio_source, audio_file_path, language: str = "en"):
-    output_audio_path = "generated_speech.wav"
-    if audio_file_path and not audio_source:
-        audio_source = audio_file_path
-
-    # Generate speech using the TTS engine
-    if audio_source is not None:
-        tts_engine.tts_to_file(input_text, speaker_wav=audio_source, language=language, file_path=output_audio_path)
+def text_to_speech(text: str, speaker_wav, speaker_wav_file, language: str):
+    if speaker_wav_file and not speaker_wav:
+        speaker_wav = speaker_wav_file
+    file_path = "output.wav"
+    if speaker_wav is not None:
+        tts.tts_to_file(text, speaker_wav=speaker_wav, language=language, file_path=file_path)
     else:
-        tts_engine.tts_to_file(input_text, speaker=tts_engine.speakers[0], language=language, file_path=output_audio_path)
-    
-    return output_audio_path
+        tts.tts_to_file(text, speaker=tts.speakers[0], language=language, file_path=file_path)
+    return file_path
 
-# Gradio interface setup
-title = "Enhanced Voice-Cloning Interface"
+title = "Prateek's Voice Cloning Demo"
 
-def audio_input_toggle(choice):
-    """Toggle audio input method based on user choice."""
+def toggle(choice):
     if choice == "mic":
         return gr.update(visible=True, value=None), gr.update(visible=False, value=None)
     else:
         return gr.update(visible=False, value=None), gr.update(visible=True, value=None)
 
-with gr.Blocks() as enhanced_demo:
+with gr.Blocks() as demo:
+    gr.Markdown("# 🎙️ Prateek's Voice Cloning Demo")
     with gr.Row():
         with gr.Column():
-            text_input = gr.Textbox(label="Enter your text here", value="", max_lines=3)
-            gr.Markdown("### Note: This demo currently supports English only.")
-            audio_method = gr.Radio(["mic", "file"], value="mic", label="Select your audio input method:")
+            text_input = gr.Textbox(label="Enter the text you want to convert to speech", value="", max_lines=3)
+            lan_input = gr.Radio(label="Language", choices=["en"], value="en", visible=False)
+            radio = gr.Radio(["Record your voice", "Upload an audio file"], value="mic",
+                             label="How would you like to provide your voice sample?")
             audio_input_mic = gr.Audio(label="Record your voice", source="microphone", type="filepath", visible=True)
-            audio_input_file = gr.Audio(label="Upload your voice file", type="filepath", visible=False)
+            audio_input_file = gr.Audio(label="Upload an audio file", type="filepath", visible=False)
 
             with gr.Row():
-                btn_clear = gr.Button("Clear")
-                btn_submit = gr.Button("Generate Speech", variant="primary")
+                with gr.Column():
+                    btn_clear = gr.Button("Clear")
+                with gr.Column():
+                    btn = gr.Button("Generate Speech", variant="primary")
         with gr.Column():
             audio_output = gr.Audio(label="Generated Speech")
 
-    btn_submit.click(convert_text_to_speech, inputs=[text_input, audio_input_mic, audio_input_file], outputs=audio_output)
-    audio_method.change(audio_input_toggle, audio_method, [audio_input_mic, audio_input_file])
+    btn.click(text_to_speech, inputs=[text_input, audio_input_mic,
+              audio_input_file, lan_input], outputs=audio_output)
+    radio.change(toggle, radio, [audio_input_mic, audio_input_file])
 
-enhanced_demo.launch(enable_queue=True)
+demo.launch(enable_queue=True)