README.md

---
title: VoxForge TTS
emoji: 🎙️
colorFrom: purple
colorTo: green
sdk: docker
pinned: false
license: mit
---

# 🎙️ VoxForge TTS — Voice Cloning Backend

A Hugging Face Space powering the **VoxForge AI** frontend app.
Built on **XTTS-v2** by Coqui — the best open-source zero-shot voice cloning model.

## What this does

| Feature | Details |
|---|---|
| Zero-shot voice clone | Upload a 6-second WAV of any voice → instant synthesis |
| 14 languages | en, es, fr, de, it, pt, pl, tr, ru, nl, cs, ar, zh-cn, ja |
| REST API | Gradio auto-exposes `/run/predict` for the HTML frontend |

## Usage

1. Upload a reference audio file (6+ seconds, WAV format)
2. Enter text to synthesize (up to 2000 characters)
3. Select language and speed
4. Click "Generate Speech"

## First Time Use

The first synthesis will take 2-5 minutes to download the 4GB model. Subsequent generations will be much faster (10-30 seconds).

## Using the REST API