Update app.py

app.py

@@ -1,55 +1,129 @@
 import gradio as gr
-from moviepy.editor import VideoFileClip, AudioFileClip, ImageClip
-
-# Function to generate audio from text (placeholder)
-def generate_audio(text, voice, rate, pitch):
-    # This should generate the audio and return an AudioFileClip
-    # Implement your audio generation logic here
-    pass
-
-# Function to create video from text and background media
-def text_to_video(text, voice, rate, pitch, bg_media, video_width, video_height):
-    # Generate the audio clip
-    audio_clip = generate_audio(text, voice, rate, pitch)  # Ensure this function is defined to generate audio
-
-    # Determine the type of background media and create the appropriate clip
-    if bg_media.endswith('.mp4'):
-        bg_clip = VideoFileClip(bg_media).set_duration(audio_clip.duration)
-    elif bg_media.endswith(('.jpg', '.png', '.jpeg')):
-        bg_clip = ImageClip(bg_media).set_duration(audio_clip.duration)
-    else:
-        return None, "Unsupported media type."
-
-    # Create a final video with audio
-    final_video = bg_clip.set_audio(audio_clip)
-
-    # Set the final output video file name
-    output_file = "output_video.mp4"
+import edge_tts
+import asyncio
+import tempfile
+import os
+from moviepy.editor import AudioFileClip
+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
+
+# SRT文件生成
+def generate_srt(pages, audio_clips):
+    srt_path = os.path.join(tempfile.gettempdir(), "output_subtitles.srt")
+    with open(srt_path, 'w', encoding='utf-8') as srt_file:
+        for i, (page, audio_clip) in enumerate(zip(pages, audio_clips)):
+            start_time = sum(audio_clip.duration for audio_clip in audio_clips[:i])
+            end_time = start_time + audio_clip.duration
+            
+            # Convert to SRT format
+            start_time_str = format_srt_time(start_time)
+            end_time_str = format_srt_time(end_time)
+            srt_file.write(f"{i + 1}\n{start_time_str} --> {end_time_str}\n{page}\n\n")
+    
+    return srt_path
+
+def format_srt_time(seconds):
+    millis = int((seconds - int(seconds)) * 1000)
+    seconds = int(seconds)
+    minutes = seconds // 60
+    hours = minutes // 60
+    minutes %= 60
+    seconds %= 60
+    return f"{hours:02}:{minutes:02}:{seconds:02},{millis:03}"
+
+# 文字转音频和SRT功能
+async def text_to_audio_and_srt(text, voice, rate, pitch):
+    # 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 = 60  # 适当设置每行最大字符数
+    max_lines_per_page = 5    # 每页最大行数
+
+    # 按页拆分文本
+    words = text.split()
+    lines = []
+    current_line = ""
+    pages = []
     
-    # Write the final video to a file
-    final_video.write_videofile(output_file, codec='libx264')
-
-    return output_file, None
-
-# Gradio interface
-def tts_interface(text, voice, rate, pitch, bg_media):
-    video, warning = text_to_video(text, voice, rate, pitch, bg_media, None, None)
-    if warning:
-        return warning
-    return video
-
-iface = gr.Interface(
-    fn=tts_interface,
-    inputs=[
-        gr.Textbox(label="Text"),
-        gr.Dropdown(label="Voice", choices=["Voice 1", "Voice 2"]),  # Update with actual voices
-        gr.Slider(label="Rate", minimum=0.5, maximum=2.0, step=0.1, value=1.0),
-        gr.Slider(label="Pitch", minimum=0, maximum=100, step=1, value=50),
-        gr.File(label="Background Media (Image/Video)")
-    ],
-    outputs="file",
-    title="Text to Video with Audio",
-    description="Upload an image or video and generate a video with audio from text."
-)
-
-iface.launch(share=True)
+    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 = []
+    for page in pages:
+        audio_text = page.replace("\n", " ")  # 移除换行符以防止 TTS 停顿
+        audio, warning = await text_to_speech(audio_text, voice, rate, pitch)
+        if warning:
+            return None, None, warning
+        audio_clip = AudioFileClip(audio)
+        audio_clips.append(audio_clip)
+
+    # 生成SRT文件
+    srt_path = generate_srt(pages, audio_clips)
+    return audio, srt_path, None
+
+# Gradio接口函数
+def tts_interface(text, voice, rate, pitch):
+    audio_path, srt_path, warning = asyncio.run(text_to_audio_and_srt(text, voice, rate, pitch))
+    return audio_path, srt_path, 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),
+        ],
+        outputs=[
+            gr.Audio(label="Generated Audio", type="filepath"),
+            gr.File(label="Generated SRT", file_count="single"),
+            gr.Markdown(label="Warning", visible=False)
+        ],
+        title="Edge TTS Text to Speech with Subtitles",
+        description="Convert text to speech and generate subtitles (SRT) using Microsoft Edge TTS.",
+        analytics_enabled=False,
+        allow_flagging=False,
+    )
+    
+    return demo
+
+# 运行应用
+if __name__ == "__main__":
+    demo = asyncio.run(create_demo())
+    demo.launch()