Spaces:
Sleeping
Sleeping
| import asyncio | |
| import os | |
| import edge_tts | |
| import gradio as gr | |
| # Function to get available voices | |
| async def get_voices(): | |
| voices = await edge_tts.list_voices() | |
| return [f"{voice['ShortName']} ({voice['Gender']})" for voice in voices] | |
| # Function to convert text to speech | |
| async def text_to_speech(text, voice, rate, pitch): | |
| try: | |
| # Extract voice ShortName from the dropdown (e.g., "en-US-AvaNeural (Female)" -> "en-US-AvaNeural") | |
| voice_short_name = voice.split(" (")[0] | |
| # Convert rate from percentage (e.g., "10" for +10%) to edge-tts format (e.g., "+10%") | |
| rate_str = f"+{int(rate)}%" if rate >= 0 else f"{int(rate)}%" | |
| # Convert pitch from Hz (e.g., "100" for +100Hz) to edge-tts format (e.g., "+100Hz") | |
| pitch_str = f"+{int(pitch)}Hz" if pitch >= 0 else f"{int(pitch)}Hz" | |
| # Generate unique output filename | |
| output_file = "output.mp3" | |
| # Initialize edge-tts communication | |
| communicate = edge_tts.Communicate(text, voice_short_name, rate=rate_str, pitch=pitch_str) | |
| # Save the audio | |
| await communicate.save(output_file) | |
| # Check if file was created | |
| if os.path.exists(output_file): | |
| return output_file | |
| else: | |
| return "Error: Audio file was not generated." | |
| except Exception as e: | |
| return f"Error: {str(e)}" | |
| # Gradio interface function | |
| def create_gradio_interface(): | |
| # Get voices synchronously | |
| loop = asyncio.get_event_loop() | |
| voices = loop.run_until_complete(get_voices()) | |
| # Define Gradio interface | |
| with gr.Blocks(title="Edge TTS Text-to-Speech") as interface: | |
| gr.Markdown("# Edge TTS Text-to-Speech") | |
| gr.Markdown("Enter text, select a voice, adjust rate and pitch, and generate audio.") | |
| # Input components | |
| text_input = gr.Textbox(label="Input Text", placeholder="Type your text here...") | |
| voice_dropdown = gr.Dropdown(choices=voices, label="Voice", value=voices[0] if voices else None) | |
| rate_slider = gr.Slider(minimum=-50, maximum=50, value=0, step=1, label="Rate (%)") | |
| pitch_slider = gr.Slider(minimum=-200, maximum=200, value=0, step=10, label="Pitch (Hz)") | |
| # Generate button | |
| generate_button = gr.Button("Generate Audio") | |
| # Output | |
| audio_output = gr.Audio(label="Generated Audio") | |
| error_output = gr.Textbox(label="Status", interactive=False) | |
| # Button click event | |
| async def on_generate(text, voice, rate, pitch): | |
| if not text: | |
| return None, "Error: Please enter some text." | |
| if not voice: | |
| return None, "Error: Please select a voice." | |
| result = await text_to_speech(text, voice, rate, pitch) | |
| if result.startswith("Error"): | |
| return None, result | |
| return result, "Audio generated successfully!" | |
| generate_button.click( | |
| fn=on_generate, | |
| inputs=[text_input, voice_dropdown, rate_slider, pitch_slider], | |
| outputs=[audio_output, error_output] | |
| ) | |
| return interface | |
| # Launch the interface | |
| if __name__ == "__main__": | |
| interface = create_gradio_interface() | |
| interface.launch(server_name="0.0.0.0", server_port=7860) |