Update app.py

app.py

@@ -5,12 +5,10 @@ from scipy.io import wavfile
 from voice_processing import tts, get_model_names, voice_mapping
 from io import BytesIO
 import asyncio
-import json
-import uuid
 
 # Constants for limits
-MAX_TEXT_FILES = 20  # Adjust the maximum number of text files processed concurrently
-MAX_WORDS = 5000  # Adjust the maximum number of words processed concurrently
+MAX_TEXT_FILES = 20  # Maximum number of text files processed concurrently
+MAX_WORDS = 5000  # Maximum number of words processed concurrently
 BATCH_SIZE = 5  # Number of texts to process in parallel
 
 async def process_tts_request(model_name, tts_text, selected_voice, slang_rate, use_uploaded_voice, voice_upload):
@@ -40,20 +38,19 @@ async def process_tts_request(model_name, tts_text, selected_voice, slang_rate,
     else:
         audio_bytes = audio_output
 
-    audio_data_uri = f"data:audio/wav;base64,{base64.b64encode(audio_bytes).decode('utf-8')}"
-    return {"info": info}, audio_data_uri
+    return {"info": info}, audio_bytes
 
 async def convert_tts(model_name, tts_texts, selected_voice, slang_rate, use_uploaded_voice, voice_upload):
     # Enforce limits
     if len(tts_texts) > MAX_TEXT_FILES:
-        return [{"error": f"Number of text files should not exceed {MAX_TEXT_FILES}."}], None
+        return {"error": f"Number of text files should not exceed {MAX_TEXT_FILES}."}, None
 
     word_count = sum(len(tts_text.split()) for tts_text in tts_texts)
     if word_count > MAX_WORDS:
-        return [{"error": f"Total number of words should not exceed {MAX_WORDS}."}], None
+        return {"error": f"Total number of words should not exceed {MAX_WORDS}."}, None
 
     # Process texts in batches
-    json_files = []
+    results = []
     for i in range(0, len(tts_texts), BATCH_SIZE):
         batch_texts = tts_texts[i:i+BATCH_SIZE]
         tasks = [
@@ -61,15 +58,12 @@ async def convert_tts(model_name, tts_texts, selected_voice, slang_rate, use_upl
             for tts_text in batch_texts
         ]
         batch_results = await asyncio.gather(*tasks)
-        for result in batch_results:
-            info, audio_uri = result
-            json_content = {"info": info, "audio_uri": audio_uri}
-            json_filename = f"{uuid.uuid4()}.json"
-            with open(json_filename, 'w') as json_file:
-                json.dump(json_content, json_file)
-            json_files.append(json_filename)
+        results.extend(batch_results)
     
-    return json_files
+    info_list = [{"info": info} for info, _ in results]
+    audio_uris = [f"data:audio/wav;base64,{base64.b64encode(audio_bytes).decode('utf-8')}" for _, audio_bytes in results]
+    
+    return info_list, audio_uris
 
 def get_models():
     return get_model_names()
@@ -88,7 +82,8 @@ iface = gr.Interface(
         gr.File(label="Voice File")
     ],
     outputs=[
-        gr.File(label="JSON Files")
+        gr.JSON(label="Info"),
+        gr.JSON(label="Audio URIs")
     ],
     title="Text-to-Speech Conversion"
 )
@@ -96,3 +91,4 @@ iface = gr.Interface(
 iface.launch()
 
 
+