README.md

January 13, 2026 · View on GitHub

Soprano-Factory: Train your own 2000x realtime text-to-speech model

Alt Text Alt Text Alt Text

soprano-github

đź“° News

2026.01.13 - Soprano-Factory released! You can now train/fine-tune your own Soprano models.

Overview

Soprano-Factory is a 600-LOC training script allowing anyone to train/fine-tune Soprano models with their own data, on their own hardware. You can use Soprano-Factory to add new voices, styles, and languages to the original Soprano model.

About Soprano

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 20x real-time generation on CPU and 2000x real-time on GPU
  • Lossless streaming with <250 ms latency on CPU, <15 ms on GPU
  • <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

Installation

git clone https://github.com/ekwek1/soprano-factory.git
cd soprano-factory
pip install -r requirements.txt

If using Windows you may need to reinstall Pytorch to have CUDA support.

Usage

1. Prepare Dataset

Soprano-Factory expects input data in LJSpeech format. Please see example_dataset for how to structure your dataset. The wav files can be in any sample rate; they will be automatically resampled to 32 kHz.

2. Dataset Preprocessing

python generate_dataset.py --input-dir path/to/files

Args:
  --input-dir:  Path to directory of LJSpeech-style dataset. If none is provided this defaults to the provided example dataset.

3. Model Training

python train.py --input-dir path/to/files --save-dir path/to/weights

Args:
  --input-dir:  Path to directory of LJSpeech-style dataset. If none is provided this defaults to the provided example dataset.
  --save-dir:   Path to directory to save weights

4. Inference

Once the model has been trained, you can then use the custom weights in the Soprano repository! Just pass your save directory into model_path.

Disclaimer

I did not originally design Soprano with finetuning in mind. As a result, I cannot guarantee that you will see good results after training.

License

This project is licensed under the Apache-2.0 license. See LICENSE for details.