Create app.py

app.py

@@ -0,0 +1,120 @@
+import gradio as gr
+import edge_tts
+import asyncio
+import tempfile
+import os
+from moviepy.editor import TextClip, concatenate_videoclips, CompositeVideoClip, AudioFileClip
+
+# 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)
+
+    # 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()
+    
+    lines.append(current_line)
+    if lines:
+        pages.append("\n".join(lines))
+
+    # 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))
+        if warning:
+            return None, warning
+        audio_clip = AudioFileClip(audio)
+        audio_clips.append(audio_clip)
+
+        # 生成视频片段
+        text_clip = TextClip(page, fontsize=text_size, font=font_path, color=text_color, size=(video_width, video_height), bg_color=bg_color, method='caption', align='center')
+        text_clip = text_clip.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)
+    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_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.ttc"),  # 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
+
+# 运行应用
+if __name__ == "__main__":
+    demo = asyncio.run(create_demo())
+    demo.launch(server_port=19856)