Update app.py

app.py

@@ -7,6 +7,7 @@ from piper import PiperVoice
 from transformers import pipeline
 import hazm
 import typing
+import os
 
 normalizer = hazm.Normalizer()
 sent_tokenizer = hazm.SentenceTokenizer()
@@ -44,11 +45,17 @@ def fix_words(words: typing.List[str]) -> typing.List[str]:
         return fixed_words
 
 def synthesize_speech(text):
-
+    # Define the directory to save audio files
+    save_dir = "audio_files"
+    if not os.path.exists(save_dir):
+        os.makedirs(save_dir)
+    
+    # Create a unique file name
+    file_name = f"audio_{np.random.randint(1000, 9999)}.wav"
+    file_path = os.path.join(save_dir, file_name)
 
     # Create an in-memory buffer for the WAV file
-    buffer = BytesIO()
-    with wave.open(buffer, 'wb') as wav_file:
+    with wave.open(file_path, 'wb') as wav_file:
         wav_file.setframerate(voice.config.sample_rate)
         wav_file.setsampwidth(2)  # 16-bit
         wav_file.setnchannels(1)  # mono
@@ -57,18 +64,21 @@ def synthesize_speech(text):
         eztext = preprocess_text(text)
         voice.synthesize(eztext, wav_file)
 
-    # Convert buffer to NumPy array for Gradio output
-    buffer.seek(0)
-    audio_data = np.frombuffer(buffer.read(), dtype=np.int16)
-
-    return audio_data.tobytes()
+    return file_path
 
 # Using Gradio Blocks
 with gr.Blocks(theme=gr.themes.Base()) as blocks:
     input_text = gr.Textbox(label="Input")
-    output_audio = gr.Audio(label="Output", type="filepath")
+    output_link = gr.Textbox(label="Output Link", type="auto", readonly=True)
     submit_button = gr.Button("Synthesize")
 
-    submit_button.click(synthesize_speech, inputs=input_text, outputs=[output_audio])
+    def synthesize_and_get_link(text):
+        file_path = synthesize_speech(text)
+        return file_path
+
+    def update_output_link(file_path):
+        return file_path
+
+    submit_button.click(synthesize_and_get_link, inputs=input_text, outputs=update_output_link)
 # Run the app
-blocks.launch()
+blocks.launch()