Spaces:
Running
Running
| import gradio as gr | |
| import edge_tts | |
| import asyncio | |
| import tempfile | |
| import os | |
| from moviepy.editor import concatenate_videoclips, AudioFileClip, ImageClip, VideoFileClip | |
| # 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} | |
| # 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.") | |
| 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 | |
| # 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 | |
| audio_clip = AudioFileClip(audio) | |
| # Check if bg_media is None | |
| if bg_media is None: | |
| return None, gr.Warning("Please upload a background image or video.") | |
| # 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)) | |
| # 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 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 | |
| # Create Gradio app | |
| 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.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), | |
| ], | |
| 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. Upload an image or video for the background.", | |
| analytics_enabled=False, | |
| allow_flagging=False, | |
| ) | |
| return demo | |
| # Run the application | |
| if __name__ == "__main__": | |
| demo = asyncio.run(create_demo()) | |
| demo.launch(share=True) # Set share=True for public link | |