File size: 1,432 Bytes
e4b9f3b 74052bf e4b9f3b 74052bf e4b9f3b 74052bf e4b9f3b 74052bf e4b9f3b 74052bf e4b9f3b fad23ac e4b9f3b 88b8d7c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 |
import gradio as gr
import edge_tts
import asyncio
import tempfile
import os
# Default voice to be used
DEFAULT_VOICE = "en-US-AndrewMultilingualNeural"
# Text-to-speech function
async def text_to_speech(text, voice=DEFAULT_VOICE, rate=0, pitch=0):
if not text.strip():
return None, gr.Warning("Please enter text to convert.")
rate_str = f"{rate:+d}%"
pitch_str = f"{pitch:+d}Hz"
communicate = edge_tts.Communicate(text, voice, 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
# Gradio interface function
def tts_interface(text):
# Pass the default voice and default values for rate and pitch
audio, warning = asyncio.run(text_to_speech(text))
return audio, warning
# Create Gradio application
async def create_demo():
demo = gr.Interface(
fn=tts_interface,
inputs=[
gr.Textbox(label="Input Text", lines=5)
],
outputs=[
gr.Audio(label="Generated Audio", type="filepath"),
gr.Markdown(label="Warning", visible=False)
],
title="Elieon TeleText AI",
analytics_enabled=False,
allow_flagging=False
)
return demo
# Run the application
if __name__ == "__main__":
demo = asyncio.run(create_demo())
demo.launch()
|