Update app.py

app.py

@@ -10,10 +10,6 @@ import os
 import requests
 from tqdm import tqdm
 
-# Initialize Gemini AI
-genai.configure(api_key='YOUR_GEMINI_API_KEY')
-model = genai.GenerativeModel('gemini-2.5-pro-preview-03-25')
-
 # Function to download the model file
 def download_model(url, filename):
     response = requests.get(url, stream=True)
@@ -67,7 +63,10 @@ filtered_state_dict = {k: v for k, v in state_dict.items() if k in model_dict}
 e2tts.load_state_dict(filtered_state_dict, strict=False)
 e2tts.eval()
 
-def generate_podcast_script(content, duration):
+def generate_podcast_script(api_key, content, duration):
+    genai.configure(api_key=api_key)
+    model = genai.GenerativeModel('gemini-2.5-pro-preview-03-25')
+    
     prompt = f"""
     Create a podcast script for two people discussing the following content:
     {content}
@@ -96,8 +95,8 @@ def text_to_speech(text, speaker_id):
     
     return sampled.cpu().numpy()
 
-def create_podcast(content, duration, voice1, voice2):
-    script = generate_podcast_script(content, duration)
+def create_podcast(api_key, content, duration, voice1, voice2):
+    script = generate_podcast_script(api_key, content, duration)
     lines = script.split('\n')
     audio_segments = []
     
@@ -113,11 +112,11 @@ def create_podcast(content, duration, voice1, voice2):
     podcast_audio = np.concatenate(audio_segments)
     return (22050, podcast_audio)  # Assuming 22050 Hz sample rate
 
-def gradio_interface(content, duration, voice1, voice2):
-    script = generate_podcast_script(content, duration)
+def gradio_interface(api_key, content, duration, voice1, voice2):
+    script = generate_podcast_script(api_key, content, duration)
     return script
 
-def render_podcast(script, voice1, voice2):
+def render_podcast(api_key, script, voice1, voice2):
     lines = script.split('\n')
     audio_segments = []
     
@@ -136,6 +135,8 @@ def render_podcast(script, voice1, voice2):
 with gr.Blocks() as demo:
     gr.Markdown("# AI Podcast Generator")
     
+    api_key_input = gr.Textbox(label="Enter your Gemini API Key", type="password")
+    
     with gr.Row():
         content_input = gr.Textbox(label="Paste your content or upload a document")
         document_upload = gr.File(label="Upload Document")
@@ -152,7 +153,7 @@ with gr.Blocks() as demo:
     render_btn = gr.Button("Render Podcast")
     audio_output = gr.Audio(label="Generated Podcast")
     
-    generate_btn.click(gradio_interface, inputs=[content_input, duration, voice1_upload, voice2_upload], outputs=script_output)
-    render_btn.click(render_podcast, inputs=[script_output, voice1_upload, voice2_upload], outputs=audio_output)
+    generate_btn.click(gradio_interface, inputs=[api_key_input, content_input, duration, voice1_upload, voice2_upload], outputs=script_output)
+    render_btn.click(render_podcast, inputs=[api_key_input, script_output, voice1_upload, voice2_upload], outputs=audio_output)
 
 demo.launch()