|
|
import gradio as gr |
|
|
import edge_tts |
|
|
import asyncio |
|
|
import tempfile |
|
|
import os |
|
|
|
|
|
|
|
|
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) |
|
|
with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp_file: |
|
|
tmp_path = tmp_file.name |
|
|
await communicate.save(tmp_path) |
|
|
return tmp_path, None |
|
|
|
|
|
def tts_interface(text, voice, rate, pitch): |
|
|
audio, warning = asyncio.run(text_to_speech(text, voice, rate, pitch)) |
|
|
return audio, warning |
|
|
|
|
|
if __name__ == "__main__": |
|
|
voices = asyncio.run(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="Speech 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.Textbox(label="Warning", visible=False) |
|
|
], |
|
|
title="ᴛᴀʟᴋᗷo᙭", |
|
|
description="📟", |
|
|
analytics_enabled=False, |
|
|
allow_flagging="manual" |
|
|
) |
|
|
demo.launch() |
|
|
|
|
|
|
