p0p4k/vits2_pytorch
unofficial vits2-TTS implementation in pytorch
This project helps generate natural-sounding speech from written text, going beyond basic text-to-speech to produce voices that are more expressive and less robotic. You provide written text and it outputs an audio file of that text spoken aloud. It is ideal for content creators, educators, or anyone needing high-quality, synthesized voices for various applications.
547 stars. No commits in the last 6 months.
Use this if you need to transform written content into highly natural and efficient spoken audio, especially for multi-speaker applications or when reducing dependence on specific phonetic conversions is important.
Not ideal if you require real-time, low-latency speech synthesis on embedded devices or if your primary goal is simple, basic text-to-speech without advanced naturalness features.
Stars
547
Forks
98
Language
Python
License
MIT
Category
Last pushed
Mar 28, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/p0p4k/vits2_pytorch"
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