|
|
--- |
|
|
license: apache-2.0 |
|
|
pipeline_tag: feature-extraction |
|
|
--- |
|
|
|
|
|
# Soprano: Instant, Ultra‑Realistic Text‑to‑Speech |
|
|
|
|
|
<div align="center"> |
|
|
|
|
|
<img width="640" height="320" alt="soprano-github" src="https://github.com/user-attachments/assets/4d612eac-23b8-44e6-8c59-d7ac14ebafd1" /> |
|
|
|
|
|
[](https://github.com/ekwek1/soprano) |
|
|
[](https://huggingface.co/spaces/ekwek/Soprano-TTS) |
|
|
</div> |
|
|
|
|
|
### 📰 News |
|
|
**2026.01.13 - [Soprano-Factory](https://github.com/ekwek1/soprano-factory) released! You can now train/fine-tune your own Soprano models.** |
|
|
2025.12.22 - Soprano-80M released! [Code](https://github.com/ekwek1/soprano) | [Demo](https://huggingface.co/spaces/ekwek/Soprano-TTS) |
|
|
|
|
|
--- |
|
|
|
|
|
This repository contains **Soprano-Encoder**, which converts raw audio into audio tokens that the LLM backbone can recognize. |
|
|
|
|
|
## Overview |
|
|
|
|
|
**Soprano** is an ultra‑lightweight, on-device text‑to‑speech (TTS) model designed for expressive, high‑fidelity speech synthesis at unprecedented speed. Soprano was designed with the following features: |
|
|
- Up to **2000x** real-time generation on GPU and **20x** real-time on CPU |
|
|
- **Lossless streaming** with **<15 ms** latency on GPU, **<250 ms** on CPU |
|
|
- **<1 GB** memory usage with a compact 80M parameter architecture |
|
|
- **Infinite generation length** with automatic text splitting |
|
|
- Highly expressive, crystal clear audio generation at **32kHz** |
|
|
- Widespread support for CUDA, CPU, and MPS devices on Windows, Linux, and Mac |
|
|
- Supports WebUI, CLI, and OpenAI-compatible endpoint for easy and production-ready inference |
|
|
|
|
|
--- |
