Create app.py

app.py

@@ -0,0 +1,49 @@
+import gradio as gr
+from TTS.api import TTS
+
+# Initialize the Text-to-Speech models
+tts_engine = TTS(model_name="tts_models/en/global/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)
+    else:
+        tts_engine.tts_to_file(input_text, speaker=tts_engine.speakers[0], language=language, file_path=output_audio_path)
+    
+    return output_audio_path
+
+# Gradio interface setup
+title = "Enhanced Voice-Cloning Interface"
+
+def audio_input_toggle(choice):
+    """Toggle audio input method based on user 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.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:")
+            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)
+
+            with gr.Row():
+                btn_clear = gr.Button("Clear")
+                btn_submit = 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])
+
+enhanced_demo.launch(enable_queue=True)