
Text-to-speech engine and voice changer by VITS
Description in other languages
Statistics
Statistics as of Nov 17, 2026
GitHub stars
92
−1 (Oct 13〜)
Last commit
Feb 2023
Created on GitHub
Dec 20, 2021
Listed
Nov 19, 2024
Stars over time
Show as a table
| Month | Stars |
|---|---|
| Dec 2025 | 91 |
| Jan 2026 | 91 |
| Feb 2026 | 91 |
| Mar 2026 | 92 |
| Apr 2026 | 92 |
| May 2026 | 92 |
| Jun 2026 | 93 |
| Jul 2026 | 93 |
| Aug 2026 | 93 |
| Sep 2026 | 93 |
| Oct 2026 | 93 |
| Nov 2026 | 92 |
Last snapshot of each month. Star counts of 1,000 or more are rounded to the nearest 100.
Popular in the same category
voicevox_engineVOICEVOX1.8kVOICEVOX is a high-quality text-to-speech software that can be used for free.
Irodori-TTSAratako1.6kA Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control
pyopenjtalkr9y9261Python wrapper for OpenJTalk
piper-plusayutaz240Enhanced Piper TTS with Japanese support, WebAssembly, multi-GPU training, and quality improvements.
AivisSpeech-EngineAivis-Project186AivisSpeech Engine: AI Voice Imitation System - Text to Speech Engine
sarashina2.2-ttssbintuitions90Sarashina2.2-TTS is a Japanese-centric text-to-speech system built on a large language model, developed by SB Intuitions.
Resources in similar research fields
voicevox_coreVOICEVOX1.2kThe core of VOICEVOX, a medium-quality text-to-speech software that can be used for free.Shared: Multimodality
jpreprocessjpreprocess61Japanese text preprocessor for Text-to-Speech applications (OpenJTalk rewrite in rust language)Shared: Multimodality- JMMMUJMMMU3kJMMMU is a Japanese multimodal benchmark expanded over tenfold to 1,320 culturally diverse questions (720 culture‑agnostic, 600 culture‑specific) translated by native subject experts, now featuring a public leaderboard.HF datasetShared: Multimodality
tacotron2-japaneseCjangCjengh265Tacotron2 implementation of JapaneseShared: Multimodality
matchaehimenlp7We have created a dataset for simplifying Japanese text from an article on the Japanese tourism media MATCHA for visitors to Japan.Shared: Multimodality
GPT-SoVITSRVC-Boss62k1 min voice data can also be used to train a good TTS model! (few shot voice cloning)MultilingualShared: Speech synthesis