Update app.py

app.py

@@ -1,3 +1,35 @@
+import gradio as gr
+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
+
+# 获取所有可用的语音
+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
+async def text_to_speech(text, voice, rate, pitch):
+    if not text.strip():
+        return None, gr.Warning("Please enter the 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
+
+# 文字转视频功能
 def text_to_video(text, voice, rate, pitch, video_width, video_height, bg_color, text_color, text_font, text_size):
     # 字体文件路径
     font_path = os.path.abspath(text_font)
@@ -49,7 +81,6 @@ def text_to_video(text, voice, rate, pitch, video_width, video_height, bg_color,
                 lines = page.split("\n")
                 for j, line in enumerate(lines):
                     draw.text(int(video_width / 2), (j + 1) * (text_size + 10), line)
-                # Apply the drawing to the image
                 draw(img)  # Correct usage to apply the drawing
                 img.format = 'png'
                 img_path = os.path.join(tempfile.gettempdir(), f"page_{i}.png")
@@ -63,6 +94,43 @@ def text_to_video(text, voice, rate, pitch, video_width, video_height, bg_color,
     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_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
+async def create_demo():
+    voices = await get_voices()
+    
+    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="Rate Adjustment (%)", step=1),
+            gr.Slider(minimum=-20, maximum=20, value=0, label="Pitch Adjustment (Hz)", step=1),
+            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.ColorPicker(value="#000000", label="Background Color"),
+            gr.ColorPicker(value="#FFFFFF", label="Text Color"),
+            gr.Textbox(label="Text Font", value="msyh.ttf"),  # 请确保字体文件路径正确
+            gr.Slider(minimum=10, maximum=100, value=24, label="Text Size", step=1)
+        ],
+        outputs=[
+            gr.Audio(label="Generated Audio", type="filepath"),
+            gr.Video(label="Generated Video"),
+            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.",
+        analytics_enabled=False,
+        allow_flagging=False,
+    )
+    
+    return demo
 
-demo.launch(share=True)
+# 运行应用
+if __name__ == "__main__":
+    demo = asyncio.run(create_demo())
+    demo.launch(share=True)  # Set share=True to create a public link