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." | |
| short_name = voice.split(" - ")[0] | |
| rate_str = f"{rate:+d}%" | |
| pitch_str = f"{pitch:+d}Hz" | |
| comm = edge_tts.Communicate(text, short_name, rate=rate_str, pitch=pitch_str) | |
| with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp: | |
| await comm.save(tmp.name) | |
| return tmp.name, "" | |
| def tts_interface(text, voice, rate, pitch): | |
| # Run asyncio in sync function | |
| audio_path, warning_text = asyncio.get_event_loop().run_until_complete( | |
| text_to_speech(text, voice, rate, pitch) | |
| ) | |
| # Return the file path (or None) and the warning string | |
| return audio_path, warning_text | |
| def build_ui(): | |
| voices = asyncio.get_event_loop().run_until_complete(get_voices()) | |
| with gr.Blocks(analytics_enabled=False) as demo: | |
| gr.Markdown("# 🎙️ Edge TTS Text-to-Speech") | |
| with gr.Row(): | |
| with gr.Column(): | |
| gr.Markdown("## Text-to-Speech with Microsoft Edge TTS") | |
| gr.Markdown( | |
| "Convert text to speech using Microsoft Edge TTS. " | |
| "Adjust rate/pitch: 0 is default, +/− to change." | |
| ) | |
| with gr.Row(): | |
| text_input = gr.Textbox(label="Input Text", lines=5) | |
| voice_dropdown = gr.Dropdown( | |
| choices=list(voices.keys()), | |
| label="Select Voice" | |
| ) | |
| rate_slider = gr.Slider(-50, 50, value=0, label="Rate (%)") | |
| pitch_slider = gr.Slider(-20, 20, value=0, label="Pitch (Hz)") | |
| generate_btn = gr.Button("Generate Speech") | |
| audio_out = gr.Audio(type="filepath", label="Output Audio") | |
| warning_md = gr.Markdown("", label="Warning") | |
| generate_btn.click( | |
| fn=tts_interface, | |
| inputs=[text_input, voice_dropdown, rate_slider, pitch_slider], | |
| outputs=[audio_out, warning_md] | |
| ) | |
| gr.Markdown( | |
| "Try our Text-to-Video converter, or tweak rate/pitch for the perfect delivery!" | |
| ) | |
| return demo | |
| if __name__ == "__main__": | |
| ui = build_ui() | |
| # Launch synchronously—no .queue(), so no internal API schema error | |
| ui.launch() | |