Update app.py

app.py

@@ -3,11 +3,27 @@ import tempfile
 import os
 from openai import OpenAI
 from gtts import gTTS
-import base64
+from gtts.lang import tts_langs
 
 # Initialize OpenAI client
 client = OpenAI(api_key=os.environ.get("OPENAI_API_KEY"))
 
+# Get available languages for Google TTS
+google_langs = tts_langs()
+
+# Define voice options for some common languages
+google_voice_options = {
+    "en": ["com.au", "ca", "co.uk", "com", "co.in", "ie", "co.za"],
+    "es": ["com", "es", "com.mx"],
+    "fr": ["fr", "ca"],
+    "de": ["de", "at"],
+    "it": ["it", "com"],
+    "ja": ["jp"],
+    "ko": ["com"],
+    "pt": ["com.br", "pt"],
+    "zh": ["cn", "tw"]
+}
+
 def openai_tts(text, voice, model):
     try:
         response = client.audio.speech.create(
@@ -16,7 +32,6 @@ def openai_tts(text, voice, model):
             input=text
         )
         
-        # Save the audio to a temporary file
         with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as temp_audio:
             temp_audio.write(response.content)
             temp_audio_path = temp_audio.name
@@ -29,18 +44,17 @@ def google_tts(text, lang, tld):
     try:
         tts = gTTS(text=text, lang=lang, tld=tld, slow=False)
         
-        # Save the audio to a temporary file
         with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as temp_audio:
             tts.save(temp_audio.name)
             temp_audio_path = temp_audio.name
 
-        return temp_audio_path, f"Speech generated with Google TTS using {lang} language and {tld} TLD"
+        return temp_audio_path, f"Speech generated with Google TTS using {lang} language and {tld} voice variant"
     except Exception as e:
         return None, f"Error in Google TTS speech generation: {str(e)}"
 
 # Gradio interface
 with gr.Blocks() as iface:
-    gr.Markdown("# OpenAI TTS and Google TTS Tool")
+    gr.Markdown("# OpenAI TTS and Enhanced Google TTS Tool")
     
     text_input = gr.Textbox(label="Enter text for speech generation")
     tts_method = gr.Radio(["OpenAI TTS", "Google TTS"], label="TTS Method", value="OpenAI TTS")
@@ -52,18 +66,18 @@ with gr.Blocks() as iface:
     
     with gr.Group() as google_options:
         gr.Markdown("Google TTS Options")
-        google_lang_input = gr.Dropdown(["en", "es", "fr", "de", "it", "ja", "ko", "pt", "ru", "zh-CN"], label="Select Language", value="en")
-        google_tld_input = gr.Dropdown(["com", "co.uk", "com.au", "co.in", "ca", "ie", "co.za"], label="Select TLD (Accent)", value="com")
+        google_lang_input = gr.Dropdown(list(google_langs.keys()), label="Select Language", value="en")
+        google_voice_input = gr.Dropdown(google_voice_options["en"], label="Select Voice Variant", value="com")
     
     speech_button = gr.Button("Generate Speech")
     speech_output = gr.Audio(label="Generated Speech")
     speech_message = gr.Textbox(label="Message")
 
-    def generate_speech(text, method, openai_voice, openai_model, google_lang, google_tld):
+    def generate_speech(text, method, openai_voice, openai_model, google_lang, google_voice):
         if method == "OpenAI TTS":
             return openai_tts(text, openai_voice, openai_model)
         else:
-            return google_tts(text, google_lang, google_tld)
+            return google_tts(text, google_lang, google_voice)
 
     def update_visible_options(method):
         return (
@@ -71,10 +85,14 @@ with gr.Blocks() as iface:
             gr.Group.update(visible=(method == "Google TTS"))
         )
 
+    def update_google_voice_options(lang):
+        return gr.Dropdown.update(choices=google_voice_options.get(lang, ["com"]), value="com")
+
     speech_button.click(generate_speech, 
-                        inputs=[text_input, tts_method, openai_voice_input, openai_model_input, google_lang_input, google_tld_input], 
+                        inputs=[text_input, tts_method, openai_voice_input, openai_model_input, google_lang_input, google_voice_input], 
                         outputs=[speech_output, speech_message])
     
     tts_method.change(update_visible_options, inputs=[tts_method], outputs=[openai_options, google_options])
+    google_lang_input.change(update_google_voice_options, inputs=[google_lang_input], outputs=[google_voice_input])
 
 iface.launch()