Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
|
@@ -10,12 +10,10 @@ VOICES = {
|
|
| 10 |
"Brian (Multilingual)": "en-US-BrianMultilingualNeural",
|
| 11 |
"Francisca": "pt-BR-FranciscaNeural",
|
| 12 |
"Thalita": "pt-BR-ThalitaNeural",
|
| 13 |
-
"Ava (
|
| 14 |
-
"Emma (
|
| 15 |
-
|
| 16 |
}
|
| 17 |
|
| 18 |
-
# Função para gerar o áudio
|
| 19 |
async def text_to_speech(text, voice):
|
| 20 |
voice_key = VOICES[voice]
|
| 21 |
output_file = f"output_{hash(text)}.mp3"
|
|
@@ -23,22 +21,67 @@ async def text_to_speech(text, voice):
|
|
| 23 |
await communicate.save(output_file)
|
| 24 |
return output_file
|
| 25 |
|
| 26 |
-
# Função para processar a entrada e chamar o TTS
|
| 27 |
async def process_tts(text, voice):
|
| 28 |
return await text_to_speech(text, voice)
|
| 29 |
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
|
| 41 |
convert_button.click(process_tts, inputs=[text_input, voice], outputs=[audio_output])
|
| 42 |
|
| 43 |
-
|
| 44 |
-
iface.launch()
|
|
|
|
| 10 |
"Brian (Multilingual)": "en-US-BrianMultilingualNeural",
|
| 11 |
"Francisca": "pt-BR-FranciscaNeural",
|
| 12 |
"Thalita": "pt-BR-ThalitaNeural",
|
| 13 |
+
"Ava (Multilingual)": "en-US-AvaMultilingualNeural",
|
| 14 |
+
"Emma (Multilingual)": "en-US-EmmaMultilingualNeural"
|
|
|
|
| 15 |
}
|
| 16 |
|
|
|
|
| 17 |
async def text_to_speech(text, voice):
|
| 18 |
voice_key = VOICES[voice]
|
| 19 |
output_file = f"output_{hash(text)}.mp3"
|
|
|
|
| 21 |
await communicate.save(output_file)
|
| 22 |
return output_file
|
| 23 |
|
|
|
|
| 24 |
async def process_tts(text, voice):
|
| 25 |
return await text_to_speech(text, voice)
|
| 26 |
|
| 27 |
+
css = """
|
| 28 |
+
body {
|
| 29 |
+
background-color: #f0f0f0;
|
| 30 |
+
font-family: 'Arial', sans-serif;
|
| 31 |
+
}
|
| 32 |
+
.container {
|
| 33 |
+
max-width: 800px;
|
| 34 |
+
margin: 0 auto;
|
| 35 |
+
padding: 20px;
|
| 36 |
+
background-color: white;
|
| 37 |
+
border-radius: 10px;
|
| 38 |
+
box-shadow: 0 0 10px rgba(0,0,0,0.1);
|
| 39 |
+
}
|
| 40 |
+
h1 {
|
| 41 |
+
color: #2c3e50;
|
| 42 |
+
text-align: center;
|
| 43 |
+
margin-bottom: 30px;
|
| 44 |
+
}
|
| 45 |
+
.footer {
|
| 46 |
+
text-align: center;
|
| 47 |
+
margin-top: 50px;
|
| 48 |
+
color: #7f8c8d;
|
| 49 |
+
font-size: 0.9em;
|
| 50 |
+
}
|
| 51 |
+
"""
|
| 52 |
+
|
| 53 |
+
with gr.Blocks(css=css) as iface:
|
| 54 |
+
with gr.Column(elem_classes="container"):
|
| 55 |
+
gr.Markdown("# TSM - Texto em Voz")
|
| 56 |
+
gr.Markdown("Converta texto em fala usando vozes em português e multilíngues.")
|
| 57 |
+
|
| 58 |
+
with gr.Row():
|
| 59 |
+
with gr.Column(scale=2):
|
| 60 |
+
text_input = gr.Textbox(
|
| 61 |
+
label="Digite o texto para converter em fala",
|
| 62 |
+
placeholder="Escreva seu texto aqui...",
|
| 63 |
+
lines=5
|
| 64 |
+
)
|
| 65 |
+
with gr.Column(scale=1):
|
| 66 |
+
voice = gr.Radio(
|
| 67 |
+
choices=list(VOICES.keys()),
|
| 68 |
+
label="Escolha a voz",
|
| 69 |
+
value="Francisca"
|
| 70 |
+
)
|
| 71 |
+
|
| 72 |
+
convert_button = gr.Button("Converter para Áudio", variant="primary")
|
| 73 |
+
audio_output = gr.Audio(label="Áudio Gerado")
|
| 74 |
+
|
| 75 |
+
gr.Markdown(
|
| 76 |
+
"""
|
| 77 |
+
<div class="footer">
|
| 78 |
+
<p>Desenvolvido por [Seu Nome/Empresa] © 2023</p>
|
| 79 |
+
<p>Powered by Azure Text-to-Speech</p>
|
| 80 |
+
</div>
|
| 81 |
+
""",
|
| 82 |
+
elem_classes="footer"
|
| 83 |
+
)
|
| 84 |
|
| 85 |
convert_button.click(process_tts, inputs=[text_input, voice], outputs=[audio_output])
|
| 86 |
|
| 87 |
+
iface.launch(show_api=False)
|
|
|