Update app.py

app.py

@@ -6,12 +6,7 @@ from voice_processing import tts, get_model_names, voice_mapping
 from io import BytesIO
 import asyncio
 
-async def async_tts(model_name, tts_text, edge_tts_voice, slang_rate, use_uploaded_voice, voice_upload_file):
-    info, edge_tts_output_path, tts_output_data, edge_output_file = await tts(
-        model_name, tts_text, edge_tts_voice, slang_rate, use_uploaded_voice, voice_upload_file
-    )
-    return info, tts_output_data
-
+# Define an asynchronous function for the Gradio interface
 async def convert_tts(model_name, tts_text, selected_voice, slang_rate, use_uploaded_voice, voice_upload):
     edge_tts_voice = voice_mapping.get(selected_voice)
     if not edge_tts_voice:
@@ -19,15 +14,17 @@ async def convert_tts(model_name, tts_text, selected_voice, slang_rate, use_uplo
 
     voice_upload_file = None
     if use_uploaded_voice and voice_upload is not None:
-        voice_upload_file = await asyncio.to_thread(voice_upload.read)
+        with open(voice_upload.name, 'rb') as f:
+            voice_upload_file = f.read()
 
-    info, tts_output_data = await async_tts(
+    # Asynchronous call to your tts processing function
+    info, edge_tts_output_path, tts_output_data, edge_output_file = await tts(
         model_name, tts_text, edge_tts_voice, slang_rate, use_uploaded_voice, voice_upload_file
     )
 
     _, audio_output = tts_output_data
 
-    # Return audio data as bytes
+    # Process audio output to bytes
     audio_bytes = None
     if isinstance(audio_output, np.ndarray):
         byte_io = BytesIO()
@@ -46,6 +43,7 @@ def get_models():
 def get_voices():
     return list(voice_mapping.keys())
 
+# Initialize the Gradio interface
 iface = gr.Interface(
     fn=convert_tts,
     inputs=[
@@ -63,5 +61,5 @@ iface = gr.Interface(
     title="Text-to-Speech Conversion"
 )
 
-iface.queue(concurrency_count=10).launch()  # Ensure concurrent handling of requests
-
+# Launch the interface
+iface.launch()