
vits
by jaywalnut310 (personal account)
VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech (description from the project’s GitHub page)
Repository facts
- Stars
- 7,894
- Forks
- 1,377
- Open issues and pull requests
- 165
- Primary language
- Python
- License
- MIT License (MIT)
- Owner
- jaywalnut310 · Personal account
- Created
- May 26, 2021
- Last push
- Dec 6, 2023
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 130: coqui-ai/TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
46,132 starsPythonMPL-2.0Last push Aug 16, 2024
Rank 957: netease-youdao/EmotiVoice
EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine
8,542 starsPythonApache-2.0Last push Sep 3, 2026
Rank 1,267: yl4579/StyleTTS2
StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
6,365 starsPythonMITLast push Aug 10, 2024
Rank 1,900: metavoiceio/metavoice-src
Foundational model for human-like, expressive TTS
4,207 starsPythonApache-2.0Last push Jul 30, 2024
Rank 3,185: jik876/hifi-gan
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
2,377 starsPythonMITLast push Jul 27, 2024
Rank 3,383: DigitalPhonetics/IMS-Toucan
Controllable and fast Text-to-Speech for over 7000 languages!
2,211 starsPythonApache-2.0Last push Jan 25, 2026