Rename txt2spec.py to steganography.py

txt2spec.py → steganography.py

@@ -7,35 +7,30 @@ import gradio as gr
 import soundfile as sf
 import os
 
-# Function for creating a spectrogram image with text
+# Функция для создания изображения спектрограммы с текстом
 def text_to_spectrogram_image(text, base_width=512, height=256, max_font_size=80, margin=10, letter_spacing=5):
-    # Font and text size
     font_path = "/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf"
     if os.path.exists(font_path):
         font = ImageFont.truetype(font_path, max_font_size)
     else:
         font = ImageFont.load_default()
 
-    # Determine the width of the text, taking into account the distance between letters
     image = Image.new('L', (base_width, height), 'black')
     draw = ImageDraw.Draw(image)
     text_width = 0
     for char in text:
         text_bbox = draw.textbbox((0, 0), char, font=font)
         text_width += text_bbox[2] - text_bbox[0] + letter_spacing
-    text_width -= letter_spacing  # Remove the extra spacing after the last letter
+    text_width -= letter_spacing
 
-    # Increase the width of the image if the text does not fit
     if text_width + margin * 2 > base_width:
         width = text_width + margin * 2
     else:
         width = base_width
 
-    # Create an image with a new width
     image = Image.new('L', (width, height), 'black')
     draw = ImageDraw.Draw(image)
     
-    # Writing text in the center of the image
     text_x = (width - text_width) // 2
     text_y = (height - (text_bbox[3] - text_bbox[1])) // 2
     for char in text:
@@ -43,78 +38,123 @@ def text_to_spectrogram_image(text, base_width=512, height=256, max_font_size=80
         char_bbox = draw.textbbox((0, 0), char, font=font)
         text_x += char_bbox[2] - char_bbox[0] + letter_spacing
     
-    # Increase text contrast
     image = np.array(image)
-    image = np.where(image > 0, 255, image)  # Setting the text to "maximum white"
+    image = np.where(image > 0, 255, image)
     return image
 
-# Converting an image to audio
+# Преобразовываем изображение в аудиосигнал
 def spectrogram_image_to_audio(image, sr=22050):
-    # Rotate the image vertically
     flipped_image = np.flipud(image)
-    
-    # Преобразуем изображение в амплитуды спектрограммы
     S = flipped_image.astype(np.float32) / 255.0 * 100.0
-    
-    # Converting the spectrogram to an audio signal
     y = librosa.griffinlim(S)
     return y
 
-# Function for creating an audio file and spectrogram from text
+# Функция для создания аудиофайла и спектрограммы из текста
 def create_audio_with_spectrogram(text, base_width, height, max_font_size, margin, letter_spacing):
-    # Create spectrogram image with normal text
     spec_image = text_to_spectrogram_image(text, base_width, height, max_font_size, margin, letter_spacing)
-    
-    # Generate audio signal with inverted text
     y = spectrogram_image_to_audio(spec_image)
-
-    # Save audio signal and spectrogram image
     audio_path = 'output.wav'
     sf.write(audio_path, y, 22050)
-    
     image_path = 'spectrogram.png'
     plt.imsave(image_path, spec_image, cmap='gray')
-
     return audio_path, image_path
 
-# Gradio interface
-with gr.Blocks(title='Audio Steganography', theme=gr.themes.Soft(primary_hue="green", secondary_hue="green", spacing_size="sm", radius_size="lg")) as iface:
+# Функция для отображения спектрограммы аудиофайла
+def display_audio_spectrogram(audio_path):
+    y, sr = librosa.load(audio_path)
+    S = librosa.feature.melspectrogram(y=y, sr=sr)
+    S_dB = librosa.power_to_db(S, ref=np.max)
+
+    plt.figure(figsize=(10, 4))
+    librosa.display.specshow(S_dB)
+    plt.tight_layout()
+
+    spectrogram_path = 'uploaded_spectrogram.png'
+    plt.savefig(spectrogram_path)
+    plt.close()
+    return spectrogram_path
+
+# Преобразование загруженного изображения в спектрограмму звука
+def image_to_spectrogram_audio(image_path, sr=22050):
+    image = Image.open(image_path).convert('L')
+    image = np.array(image)
+    y = spectrogram_image_to_audio(image, sr)
+    audio_path = 'image_to_audio_output.wav'
+    sf.write(audio_path, y, sr)
+    return audio_path
+
+# Интерфейс Gradio
+with gr.Blocks(title='Аудио-Стеганография', theme=gr.themes.Soft(primary_hue="green", secondary_hue="green", spacing_size="sm", radius_size="lg")) as iface:
     
     with gr.Group():
         with gr.Row(variant='panel'):
             with gr.Column():
-                gr.HTML("<center><h2><a href='https://t.me/pol1trees'>Telegram Channel</a></h2></center>")
+                gr.HTML("<center><h2><a href='https://t.me/pol1trees'>Telegram Канал</a></h2></center>")
             with gr.Column():
-                gr.HTML("<center><h2><a href='https://t.me/+GMTP7hZqY0E4OGRi'>Telegram Chat</a></h2></center>")
+                gr.HTML("<center><h2><a href='https://t.me/+GMTP7hZqY0E4OGRi'>Telegram Чат</a></h2></center>")
             with gr.Column():
                 gr.HTML("<center><h2><a href='https://www.youtube.com/channel/UCHb3fZEVxUisnqLqCrEM8ZA'>YouTube</a></h2></center>")
             with gr.Column():
                 gr.HTML("<center><h2><a href='https://github.com/Bebra777228/Audio-Steganography'>GitHub</a></h2></center>")
 
-    with gr.Group():
-        text = gr.Textbox(lines=2, placeholder="Enter your text:", label="Text")
+    with gr.Tab("Текст в Спектрограмму"):
+        with gr.Group():
+            text = gr.Textbox(lines=2, placeholder="Введите свой текст:", label="Текст")
+            with gr.Row(variant='panel'):
+                base_width = gr.Slider(value=512, label="Ширина изображения", visible=False)
+                height = gr.Slider(value=256, label="Высота изображения", visible=False)
+                max_font_size = gr.Slider(minimum=10, maximum=130, step=5, value=80, label="Размер шрифта")
+                margin = gr.Slider(minimum=0, maximum=50, step=1, value=10, label="Отступ")
+                letter_spacing = gr.Slider(minimum=0, maximum=50, step=1, value=5, label="Расстояние между буквами")
+            generate_button = gr.Button("Сгенерировать")
+        
+        with gr.Column(variant='panel'):
+            output_audio = gr.Audio(type="filepath", label="Сгенерированный звук")
+            output_image = gr.Image(type="filepath", label="Спектрограмма")
 
-        with gr.Row(variant='panel'):
-            base_width = gr.Slider(value=512, label="Image Width", visible=False)
-            height = gr.Slider(value=256, label="Image Height", visible=False)
-            max_font_size = gr.Slider(minimum=10, maximum=130, step=5, value=80, label="Font Size")
-            margin = gr.Slider(minimum=0, maximum=50, step=1, value=10, label="Indent")
-            letter_spacing = gr.Slider(minimum=0, maximum=50, step=1, value=5, label="Letter spacing")
+        def gradio_interface_fn(text, base_width, height, max_font_size, margin, letter_spacing):
+            return create_audio_with_spectrogram(text, base_width, height, max_font_size, margin, letter_spacing)
         
-        generate_button = gr.Button("Generate")
+        generate_button.click(
+            gradio_interface_fn,
+            inputs=[text, base_width, height, max_font_size, margin, letter_spacing],
+            outputs=[output_audio, output_image]
+        )
 
-    with gr.Column(variant='panel'):
-        output_audio = gr.Audio(type="filepath", label="Generated audio")
-        output_image = gr.Image(type="filepath", label="Spectrogram")
+    with gr.Tab("Изображение в Спектрограмму"):
+        with gr.Group():
+            with gr.Row(variant='panel'):
+                upload_image = gr.Image(type="filepath", label="Загрузите изображение")
+                convert_button = gr.Button("Конвертировать в аудио")
+            
+            with gr.Column(variant='panel'):
+                output_audio_from_image = gr.Audio(type="filepath", label="Сгенерированный звук")
 
-    def gradio_interface_fn(text, base_width, height, max_font_size, margin, letter_spacing):
-        print("\n", text)
-        return create_audio_with_spectrogram(text, base_width, height, max_font_size, margin, letter_spacing)
-    
-    generate_button.click(
-        gradio_interface_fn,
-        inputs=[text, base_width, height, max_font_size, margin, letter_spacing],
-        outputs=[output_audio, output_image]
-    )
+            def gradio_image_to_audio_fn(upload_image):
+                return image_to_spectrogram_audio(upload_image)
+            
+            convert_button.click(
+                gradio_image_to_audio_fn,
+                inputs=[upload_image],
+                outputs=[output_audio_from_image]
+            )
+
+    with gr.Tab("Спектрограмма аудио"):
+        with gr.Group():
+            with gr.Row(variant='panel'):
+                upload_audio = gr.Audio(type="filepath", label="Загрузите аудиофайл")
+                decode_button = gr.Button("Показать спектрограмму")
+            
+            with gr.Column(variant='panel'):
+                decoded_image = gr.Image(type="filepath", label="Спектрограмма аудио")
+
+            def gradio_decode_fn(upload_audio):
+                return display_audio_spectrogram(upload_audio)
+            
+            decode_button.click(
+                gradio_decode_fn,
+                inputs=[upload_audio],
+                outputs=[decoded_image]
+            )
 
 iface.launch(share=True)