Update app.py

app.py

@@ -3,17 +3,17 @@ import edge_tts
 import asyncio
 import tempfile
 import os
-from moviepy.editor import TextClip, concatenate_videoclips, CompositeVideoClip, AudioFileClip, ImageClip
+from moviepy.editor import concatenate_videoclips, AudioFileClip, ImageClip
 from wand.image import Image
 from wand.drawing import Drawing
 from wand.color import Color
 
-# 获取所有可用的语音
+# Function to get 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}
 
-# 文字转语音功能
+# Text-to-Speech function
 async def text_to_speech(text, voice, rate, pitch):
     if not text.strip():
         return None, gr.Warning("Please enter the text to convert.")
@@ -29,80 +29,64 @@ async def text_to_speech(text, voice, rate, pitch):
         await communicate.save(tmp_path)
     return tmp_path, None
 
-# 文字转视频功能
+# Text-to-Video function
 def text_to_video(text, voice, rate, pitch, video_width, video_height, bg_color, text_color, text_font, text_size):
-    # Use a built-in font for testing purposes
+    # Ensure the font file exists, else use a default font
     font_path = os.path.abspath(text_font) if os.path.exists(text_font) else "Arial"
 
-    # 计算每页可以容纳的行数和每行可以容纳的字符数
-    max_chars_per_line = video_width // (text_size // 2)  # 字体宽度假设为字体大小的一半
-    max_lines_per_page = video_height // (text_size + 15)  # 10是行间距
-
-    # 按页拆分文本
+    # Split text into lines
     words = text.split()
     lines = []
     current_line = ""
-    pages = []
     
     for word in words:
-        if len(current_line) + len(word) + 1 > max_chars_per_line:
+        if len(current_line) + len(word) + 1 > (video_width // (text_size // 2)):
             lines.append(current_line)
             current_line = word
-            if len(lines) == max_lines_per_page:
-                pages.append("\n".join(lines))
-                lines = []
         else:
             current_line = f"{current_line} {word}".strip()
     
-    lines.append(current_line)
-    if lines:
-        pages.append("\n".join(lines))
+    if current_line:
+        lines.append(current_line)
 
-    # 为每页生成独立音频
     audio_clips = []
     video_clips = []
-    for i, page in enumerate(pages):
-        # 将每页的文本连贯朗读生成一个音频文件
-        audio_text = page.replace("\n", " ")  # 移除换行符以防止 TTS 停顿
-        audio, warning = asyncio.run(text_to_speech(audio_text, voice, rate, pitch))
+
+    for line in lines:
+        audio, warning = asyncio.run(text_to_speech(line, voice, rate, pitch))
         if warning:
             return None, warning
         audio_clip = AudioFileClip(audio)
         audio_clips.append(audio_clip)
 
-        # 使用 wand 生成视频片段
+        # Create an image for each line of text
         with Drawing() as draw:
             draw.font = font_path
             draw.font_size = text_size
             draw.fill_color = Color(text_color)
-            draw.text_alignment = 'center'
-            draw.text_interline_spacing = 10
             with Image(width=video_width, height=video_height, background=Color(bg_color)) as img:
-                lines = page.split("\n")
-                for j, line in enumerate(lines):
-                    # Calculate y position based on the line index
-                    y_position = int((video_height / 2) - ((len(lines) * (text_size + 10)) / 2) + j * (text_size + 10))
-                    print(f"Drawing text: {line} at position: ({int(video_width / 2)}, {y_position})")  # Debugging line
-                    draw.text(int(video_width / 2), y_position, line)
-                draw(img)  # Correctly draw the text onto the image
-                img.format = 'png'
-                img_path = os.path.join(tempfile.gettempdir(), f"page_{i}.png")
+                # Draw the text in the center
+                text_width = draw.get_text_dimensions(line)[0]
+                y_position = (video_height - text_size) // 2  # Center vertically
+                draw.text((video_width - text_width) // 2, y_position, line)  # Center horizontally
+                draw(img)
+                img_path = os.path.join(tempfile.gettempdir(), f"{line}.png")
                 img.save(filename=img_path)
                 text_clip = ImageClip(img_path).set_duration(audio_clip.duration).set_audio(audio_clip)
                 video_clips.append(text_clip)
 
-    # 合并所有视频片段
+    # Combine all video clips
     final_video = concatenate_videoclips(video_clips)
     final_video_path = os.path.join(tempfile.gettempdir(), "output_video.mp4")
     final_video.write_videofile(final_video_path, fps=24, codec="libx264")
     return final_video_path, None
 
-# Gradio接口函数
+# Gradio interface function
 def tts_interface(text, voice, rate, pitch, video_width, video_height, bg_color, text_color, text_font, text_size):
     video, warning = text_to_video(text, voice, rate, pitch, video_width, video_height, bg_color, text_color, text_font, text_size)
     return None, video, warning
 
-# 创建Gradio应用
+# Create Gradio app
 async def create_demo():
     voices = await get_voices()
     
@@ -117,7 +101,7 @@ async def create_demo():
             gr.Slider(minimum=480, maximum=1080, value=720, label="Video Height", step=10),
             gr.ColorPicker(value="#000000", label="Background Color"),
             gr.ColorPicker(value="#FFFFFF", label="Text Color"),
-            gr.Textbox(label="Text Font", value="msyh.ttf"),  # Ensure this path is correct
+            gr.Textbox(label="Text Font", value="Arial"),  # Default to Arial for testing
             gr.Slider(minimum=10, maximum=100, value=24, label="Text Size", step=1)
         ],
         outputs=[
@@ -133,7 +117,7 @@ async def create_demo():
     
     return demo
 
-# 运行应用
+# Run the app
 if __name__ == "__main__":
     demo = asyncio.run(create_demo())
-    demo.launch(share=True)  # Change to share=True if you want a public link
+    demo.launch(share=True)