daniilrobnikov/vits2
VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design
This project helps create highly natural-sounding speech directly from written text. You provide text, and it generates high-quality audio that sounds like a human speaking, capable of both single and multi-speaker outputs. It's for anyone needing realistic voice narration for content or applications.
634 stars. No commits in the last 6 months.
Use this if you need to convert written scripts into natural, human-like speech efficiently for a variety of applications.
Not ideal if you require an extremely lightweight solution for simple text-to-speech with less emphasis on naturalness and efficiency.
Stars
634
Forks
71
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Sep 11, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/daniilrobnikov/vits2"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yeyupiaoling/MASR
Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持Conformer、Squeezeformer、DeepSpeech2模型，支持多种数据增强方法。
shivammehta25/Matcha-TTS
[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
coqui-ai/TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
DigitalPhonetics/IMS-Toucan
Controllable and fast Text-to-Speech for over 7000 languages!
gabrielmittag/NISQA
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment