Update app.py

app.py

@@ -6,7 +6,7 @@ import os
 import uuid
 from pydub import AudioSegment
 
-# Fetch available voices (filtering for English by default)
+# Fetch available voices
 async def get_voices():
     voices = await edge_tts.VoicesManager.create()
     voice_list = voices.find(Language="en")
@@ -17,62 +17,80 @@ def extract_text(pdf_file):
     doc = fitz.open(pdf_file.name)
     return "".join([page.get_text() for page in doc])
 
-# Main conversion logic
-async def convert_pdf_to_long_audio(pdf_file, voice_short_name):
+# Main conversion logic with Progress Tracker
+async def convert_pdf_to_long_audio(pdf_file, voice_short_name, progress=gr.Progress()):
+    if pdf_file is None:
+        return "Please upload a file.", None
+
+    progress(0, desc="Reading PDF...")
     text = extract_text(pdf_file)
+    
     if not text.strip():
         return "No text found in PDF.", None
 
-    # Chunking text to avoid timeout (approx 2000 chars per chunk)
-    chunks = [text[i:i+2000] for i in range(0, len(text), 2000)]
-    combined_audio = AudioSegment.empty()
+    # Chunking: ~2500 characters is a safe bet for Edge-TTS stability
+    chunk_size = 2500
+    chunks = [text[i:i+chunk_size] for i in range(0, len(text), chunk_size)]
+    total_chunks = len(chunks)
     
-    # Create a temporary directory for chunks
+    combined_audio = AudioSegment.empty()
     session_id = str(uuid.uuid4())
     os.makedirs(session_id, exist_ok=True)
 
+    # Iterating through chunks with progress updates
     for i, chunk in enumerate(chunks):
+        # Update progress bar: (current_index / total_count)
+        progress((i / total_chunks), desc=f"Converting chunk {i+1} of {total_chunks} to voice...")
+        
         chunk_path = os.path.join(session_id, f"chunk_{i}.mp3")
         communicate = edge_tts.Communicate(chunk, voice_short_name)
         await communicate.save(chunk_path)
         
-        # Load and append to the master file
+        # Load and append
         segment = AudioSegment.from_mp3(chunk_path)
         combined_audio += segment
 
-    final_path = f"output_{session_id}.mp3"
+    progress(0.95, desc="Merging all audio parts into final file...")
+    final_path = f"audiobook_{session_id}.mp3"
     combined_audio.export(final_path, format="mp3")
     
-    # Cleanup chunks
+    # Cleanup
     for f in os.listdir(session_id):
         os.remove(os.path.join(session_id, f))
     os.rmdir(session_id)
     
+    progress(1.0, desc="Done!")
     return text[:2000] + "...", final_path
 
 # Gradio Wrapper
-def process(pdf, voice_name):
-    # Map friendly name back to short name
+def process(pdf, voice_name, progress=gr.Progress()):
     voice_id = voice_dict[voice_name]
-    return asyncio.run(convert_pdf_to_long_audio(pdf, voice_id))
+    return asyncio.run(convert_pdf_to_long_audio(pdf, voice_id, progress))
 
 # Initialize voice list
 voice_dict = asyncio.run(get_voices())
 
-with gr.Blocks() as demo:
-    gr.Markdown("# 📚 PDF to Long-Form AI Audiobook")
-    gr.Markdown("Upload a PDF and choose a voice. This tool supports long files by processing text in chunks.")
+# Building the Interface
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("# 🎧 Infinite PDF Audiobook Generator")
+    gr.Markdown("Upload your PDF and wait for the AI to narrate it. **Progress is tracked below the button.**")
     
     with gr.Row():
-        pdf_input = gr.File(label="Upload PDF", file_types=[".pdf"])
-        voice_input = gr.Dropdown(choices=list(voice_dict.keys()), label="Select AI Voice", value=list(voice_dict.keys())[0])
-    
-    btn = gr.Button("Convert to Speech")
-    
-    with gr.Row():
-        text_preview = gr.Textbox(label="Text Preview (First 2000 chars)")
-        audio_output = gr.Audio(label="Full Audiobook File")
+        with gr.Column():
+            pdf_input = gr.File(label="Upload PDF", file_types=[".pdf"])
+            voice_input = gr.Dropdown(
+                choices=list(voice_dict.keys()), 
+                label="Select AI Voice", 
+                value="Microsoft Guy Online (Natural) - en-US-GuyNeural"
+            )
+            btn = gr.Button("Start Audio Conversion", variant="primary")
+        
+        with gr.Column():
+            text_preview = gr.Textbox(label="Text Preview", lines=5)
+            audio_output = gr.Audio(label="Final Audiobook (Download here)")
 
+    # The magic happens here: passing the progress bar to the function
     btn.click(process, inputs=[pdf_input, voice_input], outputs=[text_preview, audio_output])
 
-demo.launch()
+if __name__ == "__main__":
+    demo.launch()