#7575th of 81 in VoiceFor voice, speech and music
bert-vits2
Multilingual text-to-speech model combining VITS2 with BERT text features
- Stars
- 8.8k
- License
- AGPL-3.0
- Last commit
- May 2026
- Last release
- Feb 2024
- Language
- Python
8,628 on 20 Apr 20268,801 on 9 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Bert-VITS2 is a text-to-speech training and inference codebase that pairs the VITS2 backbone with multilingual BERT embeddings. The README points to webui_preprocess.py for a quick guide and expects users to read the code to learn training. The maintainers say the project will not be maintained in the short term and recommend Fish-Speech as the replacement.
Who it is for: Developers training custom TTS voices who can work from source code
Strengths
- VITS2 backbone with multilingual BERT features, building on MassTTS and vits2_pytorch
- Includes a preprocessing web UI script (webui_preprocess.py) as a starting point
- Demo and tech-slide videos are linked for judging output quality
Weaknesses
- Maintainers say it is unmaintained short term and recommend Fish-Speech instead
- Last release is February 2024
- README has no install steps, requirements or API docs; users must read the code
- AGPL-3.0 license, plus usage restrictions stated in the README
What it needs
- Models: VITS2, multilingual BERT
What changed
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Quick answers
Is bert-vits2 open source?
Yes. Its code is on GitHub under the AGPL-3.0 license.
Also in Voice
See all 81| Rank | Project | Score |
|---|---|---|
| 1 | voicestudioDesktop app for voice cloning, dubbing, dictation and audiobooks | 98 out of 100 |
| 2 | handyOffline push-to-talk dictation app that pastes transcripts into any text field | 91 out of 100 |
| 3 | whisper.cppC/C++ speech-to-text engine running OpenAI Whisper models locally | 90 out of 100 |
| #4 | xiaozhi-esp32ESP32 firmware for a voice chatbot with MCP device and cloud tool control | 83 out of 100 |
| #5 | buzzOffline desktop app for transcribing and translating audio with Whisper | 83 out of 100 |