app.py

import edge_tts
import gradio as gr
import tempfile
import anyio

# Define the available languages and their corresponding voices
language_dict = {
    "en": "en-US-JennyNeural",
    "en2": "en-US-GuyNeural",
    # Add more languages and voices as needed
}

async def text_to_speech_edge(text, language_code):
    voice = language_dict.get(language_code, "default_voice")
    communicate = edge_tts.Communicate(text, voice)
    with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as tmp_file:
        tmp_path = tmp_file.name
        await communicate.save(tmp_path)
    return f"Speech synthesis completed for: {text}", tmp_path

input_text = gr.Textbox(lines=5, label="Input Text")
output_text = gr.Textbox(label="Output Text")
output_audio = gr.Audio(type="filepath", label="Exported Audio")
language = gr.Dropdown(choices=list(language_dict.keys()), label="Language")

interface = gr.Interface(
    fn=text_to_speech_edge,
    inputs=[input_text, language],
    outputs=[output_text, output_audio],
    title="Edge TTS Text-to-Speech"
)

if __name__ == "__main__":
    anyio.run(interface.launch, backend="asyncio")