Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import edge_tts | |
| import asyncio | |
| import tempfile | |
| async def get_voices(): | |
| voices = await edge_tts.list_voices() | |
| return { | |
| f"{v['ShortName']} - {v['Locale']} ({v['Gender']})": v['ShortName'] | |
| for v in voices | |
| } | |
| async def text_to_speech(text, voice, rate, pitch): | |
| if not text.strip(): | |
| return None, "Please enter text to convert." | |
| if not voice: | |
| return None, "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) | |
| # Save directly to mp3 file | |
| with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp_file: | |
| await communicate.save(tmp_file.name) | |
| return tmp_file.name, "" | |
| async def tts_interface(text, voice, rate, pitch): | |
| audio_path, warning_text = await text_to_speech(text, voice, rate, pitch) | |
| # audio_path: str|None; warning_text: str | |
| # Return audio_path, and a Gradio update dict for the Markdown | |
| return audio_path, gr.update(value=warning_text) | |
| async def create_demo(): | |
| voices = await get_voices() | |
| with gr.Blocks(analytics_enabled=False) as demo: | |
| gr.Markdown("# 🎙️ Edge TTS Text-to-Speech") | |
| with gr.Row(): | |
| with gr.Column(scale=1): | |
| gr.Markdown("## Text-to-Speech with Microsoft Edge TTS") | |
| gr.Markdown(""" | |
| Convert text to speech using Microsoft Edge TTS. | |
| Adjust speech rate and pitch: 0 is default, positive values increase, negative values decrease. | |
| """) | |
| # (Promotional HTML omitted for brevity) | |
| with gr.Column(scale=1): | |
| # (Second promotional HTML omitted for brevity) | |
| pass | |
| with gr.Row(): | |
| with gr.Column(): | |
| text_input = gr.Textbox(label="Input Text", lines=5) | |
| voice_dropdown = gr.Dropdown( | |
| choices=[""] + list(voices.keys()), | |
| label="Select Voice", | |
| value="" | |
| ) | |
| rate_slider = gr.Slider( | |
| minimum=-50, maximum=50, value=0, | |
| label="Speech Rate Adjustment (%)", step=1 | |
| ) | |
| pitch_slider = gr.Slider( | |
| minimum=-20, maximum=20, value=0, | |
| label="Pitch Adjustment (Hz)", step=1 | |
| ) | |
| generate_btn = gr.Button("Generate Speech", variant="primary") | |
| audio_output = gr.Audio(label="Generated Audio", type="filepath") | |
| warning_md = gr.Markdown("", label="Warning") | |
| generate_btn.click( | |
| fn=tts_interface, | |
| inputs=[text_input, voice_dropdown, rate_slider, pitch_slider], | |
| outputs=[audio_output, warning_md] | |
| ) | |
| gr.Markdown( | |
| "Experience the power of Edge TTS for text-to-speech conversion, " | |
| "and explore our advanced Text-to-Video Converter for even more creative possibilities!" | |
| ) | |
| return demo | |
| async def main(): | |
| demo = await create_demo() | |
| demo.queue(default_concurrency_limit=50) | |
| demo.launch(show_api=False) | |
| if __name__ == "__main__": | |
| asyncio.run(main()) | |