Update app.py

app.py

@@ -3,17 +3,14 @@ import edge_tts
 import asyncio
 import tempfile
 import os
-from moviepy.editor import TextClip, concatenate_videoclips, CompositeVideoClip, AudioFileClip, ImageClip
-from wand.image import Image
-from wand.drawing import Drawing
-from wand.color import Color
+from moviepy.editor import concatenate_videoclips, AudioFileClip, ImageClip, VideoFileClip
 
-# 获取所有可用的语音
+# 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}
 
-# 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.")
@@ -29,95 +26,35 @@ 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
-def text_to_video(text, voice, rate, pitch, video_width, video_height, bg_image, text_color, text_font, text_size):
-    # 字体文件路径
-    font_path = os.path.abspath(text_font)
+# Text-to-video function
+def text_to_video(text, voice, rate, pitch, bg_media, video_width, video_height):
+    # Generate audio from text
+    audio, warning = asyncio.run(text_to_speech(text, voice, rate, pitch))
+    if warning:
+        return None, warning
 
-    # 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
-    words = text.split()
-    lines = []
-    current_line = ""
-    pages = []
-    
-    for word in words:
-        if len(current_line) + len(word) + 1 > max_chars_per_line:
-            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()
+    audio_clip = AudioFileClip(audio)
     
-    lines.append(current_line)
-    if lines:
-        pages.append("\n".join(lines))
-
-    # 为每页生成独立音频
-    audio_clips = []
-    video_clips = []
+    # Create background video or image
+    if bg_media.endswith('.mp4'):
+        bg_clip = VideoFileClip(bg_media).resize(newsize=(video_width, video_height)).set_duration(audio_clip.duration)
+    else:
+        bg_clip = ImageClip(bg_media).set_duration(audio_clip.duration).resize(newsize=(video_width, video_height))
     
-    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))
-        if warning:
-            return None, warning
-        audio_clip = AudioFileClip(audio)
-        audio_clips.append(audio_clip)
-
-        # 使用 wand 生成视频片段
-        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('transparent')) as img:
-                lines = page.split("\n")
-                # Centering text vertically
-                total_text_height = len(lines) * (text_size + 10)  # Height of text area
-                start_y = (video_height - total_text_height) // 2  # Start position to center vertically
-                
-                for j, line in enumerate(lines):
-                    draw.text(int(video_width / 2), start_y + (j * (text_size + 10)), line)
-                
-                draw(img)  # Apply the drawing to the image
-                img.format = 'png'
-                img_path = os.path.join(tempfile.gettempdir(), f"page_{i}.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
-    final_video = concatenate_videoclips(video_clips)
-
-    # If a background image is provided, create a CompositeVideoClip
-    if bg_image:
-        bg_clip = ImageClip(bg_image).set_duration(final_video.duration).resize(newsize=(video_width, video_height))
-        final_video = CompositeVideoClip([bg_clip, final_video.set_position("center")])
+    # Set audio for the background
+    final_video = bg_clip.set_audio(audio_clip)
 
     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
-def tts_interface(text, voice, rate, pitch, video_width, video_height, bg_image, text_color, text_font, text_size):
-    # Check if a background image is uploaded
-    if bg_image is not None:
-        video, warning = text_to_video(text, voice, rate, pitch, video_width, video_height, bg_image.name, text_color, text_font, text_size)
-    else:
-        # Pass None for the bg_image if not uploaded
-        video, warning = text_to_video(text, voice, rate, pitch, video_width, video_height, None, text_color, text_font, text_size)
+# Gradio interface function
+def tts_interface(text, voice, rate, pitch, bg_media, video_width, video_height):
+    video, warning = text_to_video(text, voice, rate, pitch, bg_media, video_width, video_height)
     return None, video, warning
 
-# 创建Gradio应用
+# Create Gradio app
 async def create_demo():
     voices = await get_voices()
     
@@ -128,12 +65,9 @@ async def create_demo():
             gr.Dropdown(choices=[""] + list(voices.keys()), label="Select Voice", value=""),
             gr.Slider(minimum=-50, maximum=50, value=0, label="Rate Adjustment (%)", step=1),
             gr.Slider(minimum=-20, maximum=20, value=0, label="Pitch Adjustment (Hz)", step=1),
+            gr.File(label="Upload Background Image or Video", type="filepath"),
             gr.Slider(minimum=640, maximum=1920, value=1080, label="Video Width", step=10),
             gr.Slider(minimum=480, maximum=1080, value=720, label="Video Height", step=10),
-            gr.File(label="Upload Background Image or Video", type="filepath"),  # Changed type to 'filepath'
-            gr.ColorPicker(value="#FFFFFF", label="Text Color"),
-            gr.Textbox(label="Text Font", value="msyh.ttf"),  # Please ensure the font file path is correct
-            gr.Slider(minimum=10, maximum=100, value=24, label="Text Size", step=1)
         ],
         outputs=[
             gr.Audio(label="Generated Audio", type="filepath"),
@@ -141,14 +75,14 @@ async def create_demo():
             gr.Markdown(label="Warning", visible=False)
         ],
         title="Edge TTS Text to Speech and Video",
-        description="Convert text to speech and video using Microsoft Edge TTS. Adjust rate and pitch: 0 is the default value, positive values increase, and negative values decrease.",
+        description="Convert text to speech and video using Microsoft Edge TTS. Upload an image or video for the background.",
         analytics_enabled=False,
         allow_flagging=False,
     )
     
     return demo
 
-# 运行应用
+# Run the application
 if __name__ == "__main__":
     demo = asyncio.run(create_demo())
     demo.launch()