app.py

import gradio as gr
import edge_tts
import asyncio
import tempfile

# Função para listar as vozes disponíveis
async def get_voices():
    voices = await edge_tts.list_voices()
    return {f"{v['ShortName']} - {v['Locale']} ({v['Gender']})": v['ShortName'] for v in voices}

# Função de texto para fala
async def text_to_speech(text, voice, rate, pitch):
    if not text.strip():
        return None, "Por favor, insira um texto para converter."
    if not voice:
        return None, "Por favor, selecione uma voz."
    
    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

# Função da interface Gradio
def tts_interface(text, voice, rate, pitch):
    audio, warning = asyncio.run(text_to_speech(text, voice, rate, pitch))
    return audio, warning

# Criar a aplicação Gradio
async def create_demo():
    voices = await get_voices()
    
    demo = gr.Interface(
        fn=tts_interface,
        inputs=[
            gr.Textbox(label="Texto de Entrada", lines=5),
            gr.Dropdown(choices=[""] + list(voices.keys()), label="Selecionar Voz", value=""),
            gr.Slider(minimum=-50, maximum=50, value=0, label="Ajuste de Taxa de Fala (%)", step=1),
            gr.Slider(minimum=-20, maximum=20, value=0, label="Ajuste de Tom (Hz)", step=1)
        ],
        outputs=[
            gr.Audio(label="Áudio Gerado", type="filepath"),
            gr.Markdown(label="Aviso", visible=False)
        ],
        title="Texto para Fala com Edge TTS",
        description="Converta texto em fala usando Microsoft Edge TTS."
    )
    return demo

# Executar a aplicação
if __name__ == "__main__":
    demo = asyncio.run(create_demo())
    demo.launch()