File structure for the Hugging Face Space: ├── app.py ├── requirements.txt └── README.md --- app.py --- import gradio as gr from transformers import pipeline Load the text-to-speech pipeline with the specified model tts = pipeline("text-to-speech", "wasmdashai/vits-ar-sa-huba-v2") Define the synthesis function def synthesize(text: str): # Generate speech from input text result = tts(text) # The pipeline returns a dict with 'audio' (np.ndarray) and 'sampling_rate' audio = result["audio"] sr = result["sampling_rate"] return sr, audio Build Gradio interface demo = gr.Interface( fn=synthesize, inputs=gr.Textbox(lines=3, label="Arabic Text for Synthesis", placeholder="اكتب نصاً هنا..."), outputs=gr.Audio(type="numpy", label="Generated Speech"), title="VITS Arabic (Saudi Hijazi) TTS", description="A demo of the vits-ar-sa-huba-v2 text-to-speech model from WasmDash AI." ) Launch the app if name == "main": demo.launch() --- requirements.txt --- gradio for UI, transformers and torch for the pipeline pin versions for reproducibility Ensure that the huggingface_hub version supports TTS pipelines gradio>=3.0 transformers>=4.32.0 torch>=1.13.0 huggingface_hub>=0.15.0 --- README.md --- VITS Arabic (Saudi Hijazi) TTS Space This Hugging Face Space demonstrates the wasmdashai/vits-ar-sa-huba-v2 text-to-speech model. Simply enter Arabic text and listen to the synthesized speech. Files app.py: Gradio application loading the TTS pipeline. requirements.txt: Python dependencies. README.md: This documentation. How to Deploy 1. Create a new Space on Hugging Face: choose SDK = "Gradio (Python)". 2. Upload these three files into the repository. 3. Your Space will automatically build and run without further edits. Enjoy!