Update app.py

app.py

@@ -1,166 +1,52 @@
 import gradio as gr
-import google.generativeai as genai
-import numpy as np
-import edge_tts
-import asyncio
+from gtts import gTTS
 import io
-import re
+import os
+from pydub import AudioSegment
 
-# Set up logging
-import logging
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
-
-# Initialize Gemini AI
-genai.configure(api_key='YOUR_GEMINI_API_KEY')
-
-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}
-    
-    The podcast should last approximately {duration}. Include natural speech patterns,
-    humor, and occasional off-topic chit-chat. Use speech fillers like um, ah,
-    yes, I see, Ok now. Vary the emotional tone.
-
-    Format the script as alternating lines of dialogue without speaker labels.
-    Do not use any special characters, markdown, or formatting. Only include the alternating dialogue lines.
-    Ensure the conversation flows naturally and stays relevant to the topic.
-    Limit the script length to match the requested duration of {duration}.
-    """
-    response = model.generate_content(prompt)
-    # Remove any special characters that might be read aloud
-    clean_text = re.sub(r'[^a-zA-Z0-9\s.,?!]', '', response.text)
-    return clean_text
-
-async def text_to_speech(text, voice):
-    communicate = edge_tts.Communicate(text, voice)
-    audio = io.BytesIO()
-    async for chunk in communicate.stream():
-        if chunk["type"] == "audio":
-            audio.write(chunk["data"])
-    audio.seek(0)
-    return audio.read()
-
-async def render_podcast(api_key, script, voice1, voice2):
-    lines = script.split('\n')
+def text_to_speech(text):
+    lines = text.split('\n')
     audio_segments = []
-    
+
     for i, line in enumerate(lines):
         if line.strip():  # Skip empty lines
-            voice = voice1 if i % 2 == 0 else voice2
-            audio = await text_to_speech(line, voice)
-            audio_segments.append(audio)
-    
-    if not audio_segments:
-        logger.warning("No valid audio segments were generated.")
-        return (24000, np.zeros(24000, dtype=np.int16))  # Return silence if no valid audio was generated
-    
-    # Concatenate audio segments
-    podcast_audio = b''.join(audio_segments)
-    
-    # Convert to numpy array
-    podcast_audio = np.frombuffer(podcast_audio, dtype=np.int16)
-    
-    return (24000, podcast_audio)  # edge-tts uses 24000 Hz sample rate
-
-async def get_voice_list():
-    voices = await edge_tts.list_voices()
-    voice_dict = {}
-    for voice in voices:
-        lang = voice["Locale"]
-        if lang not in voice_dict:
-            voice_dict[lang] = []
-        voice_dict[lang].append(voice["Name"])
-    return voice_dict
-
-# Language names dictionary
-language_names = {
-    'af-ZA': 'Afrikaans (South Africa)', 'am-ET': 'Amharic (Ethiopia)', 'ar-AE': 'Arabic (UAE)', 'ar-BH': 'Arabic (Bahrain)',
-    'ar-DZ': 'Arabic (Algeria)', 'ar-EG': 'Arabic (Egypt)', 'ar-IQ': 'Arabic (Iraq)', 'ar-JO': 'Arabic (Jordan)',
-    'ar-KW': 'Arabic (Kuwait)', 'ar-LB': 'Arabic (Lebanon)', 'ar-LY': 'Arabic (Libya)', 'ar-MA': 'Arabic (Morocco)',
-    'ar-OM': 'Arabic (Oman)', 'ar-QA': 'Arabic (Qatar)', 'ar-SA': 'Arabic (Saudi Arabia)', 'ar-SY': 'Arabic (Syria)',
-    'ar-TN': 'Arabic (Tunisia)', 'ar-YE': 'Arabic (Yemen)', 'az-AZ': 'Azerbaijani (Azerbaijan)', 'bg-BG': 'Bulgarian (Bulgaria)',
-    'bn-BD': 'Bengali (Bangladesh)', 'bn-IN': 'Bengali (India)', 'bs-BA': 'Bosnian (Bosnia and Herzegovina)', 'ca-ES': 'Catalan (Spain)',
-    'cs-CZ': 'Czech (Czech Republic)', 'cy-GB': 'Welsh (United Kingdom)', 'da-DK': 'Danish (Denmark)', 'de-AT': 'German (Austria)',
-    'de-CH': 'German (Switzerland)', 'de-DE': 'German (Germany)', 'el-GR': 'Greek (Greece)', 'en-AU': 'English (Australia)',
-    'en-CA': 'English (Canada)', 'en-GB': 'English (United Kingdom)', 'en-GH': 'English (Ghana)', 'en-HK': 'English (Hong Kong SAR)',
-    'en-IE': 'English (Ireland)', 'en-IN': 'English (India)', 'en-KE': 'English (Kenya)', 'en-NG': 'English (Nigeria)',
-    'en-NZ': 'English (New Zealand)', 'en-PH': 'English (Philippines)', 'en-SG': 'English (Singapore)', 'en-TZ': 'English (Tanzania)',
-    'en-US': 'English (United States)', 'en-ZA': 'English (South Africa)', 'es-AR': 'Spanish (Argentina)', 'es-BO': 'Spanish (Bolivia)',
-    'es-CL': 'Spanish (Chile)', 'es-CO': 'Spanish (Colombia)', 'es-CR': 'Spanish (Costa Rica)', 'es-CU': 'Spanish (Cuba)',
-    'es-DO': 'Spanish (Dominican Republic)', 'es-EC': 'Spanish (Ecuador)', 'es-ES': 'Spanish (Spain)', 'es-GQ': 'Spanish (Equatorial Guinea)',
-    'es-GT': 'Spanish (Guatemala)', 'es-HN': 'Spanish (Honduras)', 'es-MX': 'Spanish (Mexico)', 'es-NI': 'Spanish (Nicaragua)',
-    'es-PA': 'Spanish (Panama)', 'es-PE': 'Spanish (Peru)', 'es-PR': 'Spanish (Puerto Rico)', 'es-PY': 'Spanish (Paraguay)',
-    'es-SV': 'Spanish (El Salvador)', 'es-US': 'Spanish (United States)', 'es-UY': 'Spanish (Uruguay)', 'es-VE': 'Spanish (Venezuela)',
-    'et-EE': 'Estonian (Estonia)', 'eu-ES': 'Basque (Spain)', 'fa-IR': 'Persian (Iran)', 'fi-FI': 'Finnish (Finland)',
-    'fil-PH': 'Filipino (Philippines)', 'fr-BE': 'French (Belgium)', 'fr-CA': 'French (Canada)', 'fr-CH': 'French (Switzerland)',
-    'fr-FR': 'French (France)', 'ga-IE': 'Irish (Ireland)', 'gl-ES': 'Galician (Spain)', 'gu-IN': 'Gujarati (India)',
-    'he-IL': 'Hebrew (Israel)', 'hi-IN': 'Hindi (India)', 'hr-HR': 'Croatian (Croatia)', 'hu-HU': 'Hungarian (Hungary)',
-    'hy-AM': 'Armenian (Armenia)', 'id-ID': 'Indonesian (Indonesia)', 'is-IS': 'Icelandic (Iceland)', 'it-IT': 'Italian (Italy)',
-    'ja-JP': 'Japanese (Japan)', 'jv-ID': 'Javanese (Indonesia)', 'ka-GE': 'Georgian (Georgia)', 'kk-KZ': 'Kazakh (Kazakhstan)',
-    'km-KH': 'Khmer (Cambodia)', 'kn-IN': 'Kannada (India)', 'ko-KR': 'Korean (Korea)', 'lo-LA': 'Lao (Laos)',
-    'lt-LT': 'Lithuanian (Lithuania)', 'lv-LV': 'Latvian (Latvia)', 'mk-MK': 'Macedonian (North Macedonia)', 'ml-IN': 'Malayalam (India)',
-    'mn-MN': 'Mongolian (Mongolia)', 'mr-IN': 'Marathi (India)', 'ms-MY': 'Malay (Malaysia)', 'mt-MT': 'Maltese (Malta)',
-    'my-MM': 'Burmese (Myanmar)', 'nb-NO': 'Norwegian (Bokmål, Norway)', 'ne-NP': 'Nepali (Nepal)', 'nl-BE': 'Dutch (Belgium)',
-    'nl-NL': 'Dutch (Netherlands)', 'pl-PL': 'Polish (Poland)', 'ps-AF': 'Pashto (Afghanistan)', 'pt-BR': 'Portuguese (Brazil)',
-    'pt-PT': 'Portuguese (Portugal)', 'ro-RO': 'Romanian (Romania)', 'ru-RU': 'Russian (Russia)', 'si-LK': 'Sinhala (Sri Lanka)',
-    'sk-SK': 'Slovak (Slovakia)', 'sl-SI': 'Slovenian (Slovenia)', 'so-SO': 'Somali (Somalia)', 'sq-AL': 'Albanian (Albania)',
-    'sr-RS': 'Serbian (Serbia)', 'sv-SE': 'Swedish (Sweden)', 'sw-KE': 'Swahili (Kenya)', 'sw-TZ': 'Swahili (Tanzania)',
-    'ta-IN': 'Tamil (India)', 'ta-LK': 'Tamil (Sri Lanka)', 'ta-MY': 'Tamil (Malaysia)', 'ta-SG': 'Tamil (Singapore)',
-    'te-IN': 'Telugu (India)', 'th-TH': 'Thai (Thailand)', 'tr-TR': 'Turkish (Turkey)', 'uk-UA': 'Ukrainian (Ukraine)',
-    'ur-IN': 'Urdu (India)', 'ur-PK': 'Urdu (Pakistan)', 'uz-UZ': 'Uzbek (Uzbekistan)', 'vi-VN': 'Vietnamese (Vietnam)',
-    'wuu-CN': 'Wu Chinese (China)', 'yue-CN': 'Cantonese (China)', 'zh-CN': 'Chinese (Mandarin, Simplified)',
-    'zh-HK': 'Chinese (Cantonese, Traditional)', 'zh-TW': 'Chinese (Taiwanese Mandarin)', 'zu-ZA': 'Zulu (South Africa)'
-}
-
-# Gradio Interface
-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")
-    
-    duration = gr.Radio(["1-5 min", "5-10 min", "10-15 min"], label="Estimated podcast duration")
-    
-    voice_dict = asyncio.run(get_voice_list())
-    languages = list(voice_dict.keys())
-    
-    with gr.Row():
-        lang1_select = gr.Dropdown(label="Select Language 1", choices=[f"{language_names.get(lang, lang)}" for lang in languages], value="English (United States)")
-        voice1_select = gr.Dropdown(label="Select Voice 1", choices=voice_dict.get('en-US', []), value="en-US-AnaNeural")
-    
-    with gr.Row():
-        lang2_select = gr.Dropdown(label="Select Language 2", choices=[f"{language_names.get(lang, lang)}" for lang in languages], value="English (United States)")
-        voice2_select = gr.Dropdown(label="Select Voice 2", choices=voice_dict.get('en-US', []), value="en-US-MichelleNeural")
-    
-    generate_btn = gr.Button("Generate Script")
-    script_output = gr.Textbox(label="Generated Script", lines=10)
-    
-    render_btn = gr.Button("Render Podcast")
-    audio_output = gr.Audio(label="Generated Podcast")
-    
-    def update_voices(lang):
-        selected_lang = next((key for key, value in language_names.items() if value == lang), None)
-        return gr.Dropdown(choices=voice_dict.get(selected_lang, []))
-    
-    lang1_select.change(update_voices, inputs=[lang1_select], outputs=[voice1_select])
-    lang2_select.change(update_voices, inputs=[lang2_select], outputs=[voice2_select])
-    
-    def generate_script_wrapper(api_key, content, duration):
-        return generate_podcast_script(api_key, content, duration)
-    
-    async def render_podcast_wrapper(api_key, script, voice1, voice2):
-        return await render_podcast(api_key, script, voice1, voice2)
-    
-    generate_btn.click(generate_script_wrapper, inputs=[api_key_input, content_input, duration], outputs=script_output)
-    render_btn.click(render_podcast_wrapper, inputs=[api_key_input, script_output, voice1_select, voice2_select], outputs=audio_output)
+            tts = gTTS(text=line, lang='en', slow=False)
+            
+            # Save to a temporary file
+            temp_filename = f"temp_{i}.mp3"
+            tts.save(temp_filename)
+            
+            # Load the audio segment
+            audio_segment = AudioSegment.from_mp3(temp_filename)
+            
+            # Alternate between two voices
+            if i % 2 == 0:
+                audio_segment = audio_segment.set_frame_rate(44100)  # Higher pitch for even lines (speaker 1)
+            else:
+                audio_segment = audio_segment.set_frame_rate(22050)  # Lower pitch for odd lines (speaker 2)
+            
+            audio_segments.append(audio_segment)
+            
+            # Remove the temporary file
+            os.remove(temp_filename)
+
+    # Concatenate all audio segments
+    final_audio = sum(audio_segments)
+
+    # Export the final audio to a byte stream
+    buffer = io.BytesIO()
+    final_audio.export(buffer, format="mp3")
+    buffer.seek(0)
+
+    return buffer
+
+iface = gr.Interface(
+    fn=text_to_speech,
+    inputs=gr.Textbox(lines=10, placeholder="Enter your text here..."),
+    outputs=gr.Audio(type="binary"),
+    title="Two-Speaker Text-to-Speech Converter",
+    description="Convert text to speech with alternating voices for even and odd lines."
+)
 
 if __name__ == "__main__":
-    demo.launch()
+    iface.launch()