vits
VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
GraphCanon updated 3w · GitHub synced 3w
Decision brief
VITS stands out in high-quality end-to-end text-to-speech applications due to its integration of variational inference with normalizing flows and adversarial training methods.
Good fit when
- Use VITS when you need a single-stage TTS model that generates high-quality, natural-sounding audio similar to ground-truth quality.
- VITS is recommended for users requiring expressivity in synthesized speech, as it includes a stochastic duration predictor enabling diverse rhythmic variations.
Avoid when
- Avoid VITS if your project requires low hardware resources. The model's high-quality output comes at the cost of higher computational demands.
- Do not opt for VITS if your application strictly needs real-time performance, as it prioritizes sample quality over speed through complex inference processes.
- Requirements:
- Min 8 GB RAM; Python >= 3.6 is required. Ensure dependencies like espeak are installed.; The model requires specific datasets: LJ Speech for single-speaker and VCTK for multi-speaker scenarios, with necessary preprocessing.
Observed Jul 17, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (966d since push)
- As of 3w
- Provenance
- Not a fork · Personal account
- As of 3w
- Security (OSV)
- 37 low (37 low)
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install vitsSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
A parallel end-to-end text-to-speech model that generates high-quality audio through variational inference, normalizing flows, and adversarial training.
Capability facts
- Languages
- python
Source: github.language · Jul 29, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Tags
README
VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
Jaehyeon Kim, Jungil Kong, and Juhee Son
In our recent paper, we propose VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech.
Several recent end-to-end text-to-speech (TTS) models enabling single-stage training and parallel sampling have been proposed, but their sample quality does not match that of two-stage TTS systems. In this work, we present a parallel end-to-end TTS method that generates more natural sounding audio than current two-stage models. Our method adopts variational inference augmented with normalizing flows and an adversarial training process, which improves the expressive power of generative modeling. We also propose a stochastic duration predictor to synthesize speech with diverse rhythms from input text. With the uncertainty modeling over latent variables and the stochastic duration predictor, our method expresses the natural one-to-many relationship in which a text input can be spoken in multiple ways with different pitches and rhythms. A subjective human evaluation (mean opinion score, or MOS) on the LJ Speech, a single speaker dataset, shows that our method outperforms the best publicly available TTS systems and achieves a MOS comparable to ground truth.
Visit our demo for audio samples.
We also provide the pretrained models.
** Update note: Thanks to Rishikesh (ऋषिकेश), our interactive TTS demo is now available on Colab Notebook.
| VITS at training | VITS at inference |
|---|---|
Pre-requisites
- Python >= 3.6
- Clone this repository
- Install python requirements. Please refer requirements.txt
- You may need to install espeak first:
apt-get install espeak
- You may need to install espeak first:
- Download datasets
- Download and extract the LJ Speech dataset, then rename or create a link to the dataset folder:
ln -s /path/to/LJSpeech-1.1/wavs DUMMY1 - For mult-speaker setting, download and extract the VCTK dataset, and downsample wav files to 22050 Hz. Then rename or create a link to the dataset folder:
ln -s /path/to/VCTK-Corpus/downsampled_wavs DUMMY2
- Download and extract the LJ Speech dataset, then rename or create a link to the dataset folder:
- Build Monotonic Alignment Search and run preprocessing if you use your own datasets.
# Cython-version Monotonoic Alignment Search
cd monotonic_align
python setup.py build_ext --inplace
# Preprocessing (g2p) for your own datasets. Preprocessed phonemes for LJ Speech and VCTK have been already provided.
# python preprocess.py --text_index 1 --filelists filelists/ljs_audio_text_train_filelist.txt filelists/ljs_audio_text_val_filelist.txt filelists/ljs_audio_text_test_filelist.txt
# python preprocess.py --text_index 2 --filelists filelists/vctk_audio_sid_text_train_filelist.txt filelists/vctk_audio_sid_text_val_filelist.txt filelists/vctk_audio_sid_text_test_filelist.txt
Training Exmaple
# LJ Speech
python train.py -c configs/ljs_base.json -m ljs_base
# VCTK
python train_ms.py -c configs/vctk_base.json -m vctk_base
Inference Example
See inference.ipynb
For agents
This page has a .md twin and JSON over the API.