Update app.py

app.py

@@ -1,55 +1,65 @@
 import gradio as gr
-import requests
-from gtts import gTTS  # Import gTTS for Text-to-Speech
+import edge_tts
+import asyncio
 import tempfile
+import os
 
-# Function to convert text to speech and transcribe
-def text_to_speech_transcribe(text):
-    # Convert text to speech
-    tts = gTTS(text, lang='en')
-    with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as tmp_audio:
-        audio_path = tmp_audio.name
-        tts.save(audio_path)
-    
-    # Read audio file in binary mode
-    with open(audio_path, "rb") as audio_file:
-        audio_data = audio_file.read()
-
-    # Groq API endpoint for audio transcription
-    groq_api_endpoint = "https://api.groq.com/openai/v1/audio/transcriptions"
+# Get all available voices
+async def get_voices():
+    voices = await edge_tts.list_voices()
+    return {f"{v['ShortName']} - {v['Locale']} ({v['Gender']})": v['ShortName'] for v in voices}
 
-    # Replace 'YOUR_GROQ_API_KEY' with your actual Groq API key
-    headers = {
-        "Authorization": "Bearer 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",  # Replace with your Groq API key
-    }
-
-    # Prepare the files and data for the request
-    files = {
-        'file': ('audio.wav', audio_data, 'audio/wav'),
-    }
-    data = {
-        'model': 'whisper-large-v3-turbo',  # Specify the model to use
-        'response_format': 'json',          # Desired response format
-        'language': 'en',                   # Language of the audio
-    }
+# Text-to-speech function
+async def text_to_speech(text, voice, rate, pitch):
+    if not text.strip():
+        return None, gr.Warning("Please enter text to convert.")
+    if not voice:
+        return None, gr.Warning("Please select a voice.")
+    
+    voice_short_name = voice.split(" - ")[0]
+    rate_str = f"{rate:+d}%"
+    pitch_str = f"{pitch:+d}Hz"
+    communicate = edge_tts.Communicate(text, voice_short_name, rate=rate_str, pitch=pitch_str)
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp_file:
+        tmp_path = tmp_file.name
+        await communicate.save(tmp_path)
+    return tmp_path, None
 
-    # Send audio to Groq API
-    response = requests.post(groq_api_endpoint, headers=headers, files=files, data=data)
+# Gradio interface function
+def tts_interface(text, voice, rate, pitch):
+    audio, warning = asyncio.run(text_to_speech(text, voice, rate, pitch))
+    return audio, warning
 
-    # Parse response
-    if response.status_code == 200:
-        result = response.json()
-        return result.get("text", "No transcription available.")
-    else:
-        return f"Error: {response.status_code}, {response.text}"
+# Create Gradio application
+import gradio as gr
 
-# Gradio interface
-iface = gr.Interface(
-    fn=text_to_speech_transcribe,
-    inputs="text",  # Input text to be converted to speech
-    outputs="text",
-    title="Text to Speech and Transcription",
-    description="Enter text to convert it to audio, then transcribe it with the Groq API."
-)
+async def create_demo():
+    voices = await get_voices()
+    
+    description = """
+    
+    
+    demo = gr.Interface(
+        fn=tts_interface,
+        inputs=[
+            gr.Textbox(label="Input Text", lines=5),
+            gr.Dropdown(choices=[""] + list(voices.keys()), label="Select Voice", value=""),
+            gr.Slider(minimum=-50, maximum=50, value=0, label="Speech Rate Adjustment (%)", step=1),
+            gr.Slider(minimum=-20, maximum=20, value=0, label="Pitch Adjustment (Hz)", step=1)
+        ],
+        outputs=[
+            gr.Audio(label="Generated Audio", type="filepath"),
+            gr.Markdown(label="Warning", visible=False)
+        ],
+        title="Edge TTS Text-to-Speech",
+        description=description,
+        article="Experience the power of Edge TTS for text-to-speech conversion, and explore our advanced Text-to-Video Converter for even more creative possibilities!",
+        analytics_enabled=False,
+        allow_flagging="manual"
+    )
+    return demo
 
-iface.launch()
+# Run the application
+if __name__ == "__main__":
+    demo = asyncio.run(create_demo())
+    demo.launch()