Update app.py

app.py

@@ -4,19 +4,12 @@ import asyncio
 import tempfile
 import re
 import emoji
-import requests
-from PIL import Image
-from io import BytesIO
-from huggingface_hub import InferenceClient
-import os
-from dotenv import load_dotenv
-
-# Загрузка переменных окружения из .env файла
-load_dotenv()
 
 # Функция для очистки текста от нежелательных символов и эмодзи
 def clean_text(text):
+    # Удаление указанных символов
     text = re.sub(r'[*_~><]', '', text)
+    # Удаление эмодзи
     text = emoji.replace_emoji(text, replace='')
     return text
 
@@ -32,7 +25,9 @@ async def text_to_speech(text, voice, rate, pitch):
     if not voice:
         return None, "Please select a voice."
     
+    # Очистка текста
     text = clean_text(text)
+    
     voice_short_name = voice.split(" - ")[0]
     rate_str = f"{rate:+d}%"
     pitch_str = f"{pitch:+d}Hz"
@@ -45,95 +40,40 @@ async def text_to_speech(text, voice, rate, pitch):
             return None, f"An error occurred during text-to-speech conversion: {str(e)}"
     return tmp_path, None
 
-# Generate image using your custom prompt and API
-def generate_image_with_prompt(prompt, api_key):
-    client = InferenceClient(
-        provider="together",
-        api_key=api_key
-    )
-    messages = [
-        {
-            "role": "user",
-            "content": prompt
-        }
-    ]
-    completion = client.chat.completions.create(
-        model="deepseek-ai/DeepSeek-R1", 
-        messages=messages, 
-        max_tokens=500
-    )
-    response = completion.choices[0].message.content
-    # Assuming the response contains a URL or image data
-    if "http" in response:
-        image_url = response
-        image_response = requests.get(image_url)
-        image = Image.open(BytesIO(image_response.content))
-        return image
-    else:
-        return None, "Failed to generate image."
-
 # Gradio interface function
 def tts_interface(*args):
     loop = asyncio.new_event_loop()
     asyncio.set_event_loop(loop)
-    audio, warning = loop.run_until_complete(text_to_speech(*args[:-2]))
-    prompt = args[-2]
-    image = generate_image_with_prompt(prompt, args[-1])
+    audio, warning = loop.run_until_complete(text_to_speech(*args))
     loop.close()
     if warning:
-        return (None, gr.update(value=f"<span style='color:red;'>{warning}</span>", visible=True), None)
-    return (audio, gr.update(visible=False), image)
+        return None, gr.update(value=f"<span style='color:red;'>{warning}</span>", visible=True)
+    return audio, gr.update(visible=False)
 
 # Create Gradio application
-async def create_demo(api_key):
+async def create_demo():
     voices = await get_voices()
     
     description = """
-    This is a simple text-to-speech and image generation application.
-    Enter any text to convert it into speech and describe an image to generate it.
+    This is a simple text-to-speech application using Microsoft Edge TTS.
+    You can enter any text and select the voice you want to use.
     Adjust the speech rate and pitch according to your preference.
     """
 
-    css = """
-    .gradio-container {
-        background: linear-gradient(135deg, #e0eafc, #cfdef3);
-        color: #333;
-    }
-    .gr-button {
-        background-color: #007aff;
-        color: white;
-    }
-    .gr-button:hover {
-        background-color: #005bb5;
-    }
-    .gr-textbox, .gr-slider, .gr-dropdown {
-        border-radius: 8px;
-        padding: 10px;
-        margin: 10px 0;
-    }
-    .gr-markdown {
-        color: red;
-    }
-    """
-
     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),
-            gr.Textbox(label="Image Prompt", lines=2),
-            gr.Textbox(label="Hugging Face API Key", value=api_key, type="password")
+            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),
-            gr.Image(label="Generated Image")
+            gr.Markdown(label="Warning", visible=False)
         ],
-        title="Edge TTS Text-to-Speech & Image Generation",
+        title="Edge TTS Text-to-Speech",
         description=description,
-        css=css,
         article="",
         analytics_enabled=False,
         allow_flagging="manual"
@@ -142,8 +82,5 @@ async def create_demo(api_key):
 
 # Run the application
 if __name__ == "__main__":
-    api_key = os.getenv('HUGGING_FACE_API_KEY')  # Ваш API ключ
-    if not api_key:
-        raise ValueError("Please set the HUGGING_FACE_API_KEY environment variable.")
-    demo = asyncio.run(create_demo(api_key))
-    demo.launch()
+    demo = asyncio.run(create_demo())
+    demo.launch()