keonlee9420/Comprehensive-E2E-TTS
A Non-Autoregressive End-to-End Text-to-Speech (text-to-wav), supporting a family of SOTA unsupervised duration modelings. This project grows with the research community, aiming to achieve the ultimate E2E-TTS
This project helps you transform written text into natural-sounding spoken audio. You provide the text you want to be spoken, and it generates an audio file (waveform) of that text. This is ideal for content creators, educators, or businesses who need to convert large amounts of text into voiceovers, audio articles, or synthetic speech for various applications.
146 stars. No commits in the last 6 months.
Use this if you need to quickly and efficiently generate high-quality, natural-sounding speech from text, with options to control pitch, volume, and speaking rate.
Not ideal if you require real-time, interactive speech generation for conversational AI, or if you need to clone specific voices without prior training data.
Stars
146
Forks
19
Language
Python
License
—
Category
Last pushed
Jun 06, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/keonlee9420/Comprehensive-E2E-TTS"
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