Create app.py

app.py

@@ -0,0 +1,16 @@
+import gradio as gr
+import os
+def inference(text):
+  os.system('tts --text ' + text)
+  return 'tts_output.wav'
+  
+inputs = gr.inputs.Textbox(lines=5, label="Input Text")
+outputs =  gr.outputs.Audio(type="file",label="Output Audio")
+title = "VITS"
+description = "demo for VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech. To use it, simply add your text, or click one of the examples to load them. Read more at the links below."
+article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2106.06103'>Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech</a> | <a href='https://github.com/jaywalnut310/vits'>Github Repo</a></p>"
+examples = [
+ ["We propose VITS, Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech."],
+ ["Our method adopts variational inference augmented with normalizing flows and an adversarial training process, which improves the expressive power of generative modeling."]   
+]
+gr.Interface(inference, inputs, outputs, title=title, description=description, article=article, examples=examples).launch()