Update app.py

app.py

@@ -71,12 +71,52 @@ async def get_voice_list():
     voices = await edge_tts.list_voices()
     voice_dict = {}
     for voice in voices:
-        lang = voice["Locale"].split("-")[0]
+        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")
@@ -91,25 +131,13 @@ with gr.Blocks() as demo:
     
     voice_dict = asyncio.run(get_voice_list())
     languages = list(voice_dict.keys())
-    language_names = {
-        'en': 'English',
-        'es': 'Spanish',
-        'fr': 'French',
-        'de': 'German',
-        'it': 'Italian',
-        'ja': 'Japanese',
-        'ko': 'Korean',
-        'pt': 'Portuguese',
-        'ru': 'Russian',
-        'zh': 'Chinese'
-    }
     
     with gr.Row():
-        lang1_select = gr.Dropdown(label="Select Language 1", choices=[f"{language_names.get(lang, lang)} ({lang})" for lang in languages])
+        lang1_select = gr.Dropdown(label="Select Language 1", choices=[f"{language_names.get(lang, lang)}" for lang in languages])
         voice1_select = gr.Dropdown(label="Select Voice 1")
     
     with gr.Row():
-        lang2_select = gr.Dropdown(label="Select Language 2", choices=[f"{language_names.get(lang, lang)} ({lang})" for lang in languages])
+        lang2_select = gr.Dropdown(label="Select Language 2", choices=[f"{language_names.get(lang, lang)}" for lang in languages])
         voice2_select = gr.Dropdown(label="Select Voice 2")
     
     generate_btn = gr.Button("Generate Script")
@@ -119,8 +147,8 @@ with gr.Blocks() as demo:
     audio_output = gr.Audio(label="Generated Podcast")
     
     def update_voices(lang):
-        lang_code = lang.split('(')[-1].strip(')')
-        return gr.Dropdown.update(choices=voice_dict[lang_code])
+        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])