SungFeng-Huang/Meta-TTS
Official repository of https://doi.org/10.1109/TASLP.2022.3167258. More up-to-date code is in "refactor" branch.
This project helps researchers and developers working on text-to-speech (TTS) systems to create new voices with very little audio data. It takes text and a small sample of a speaker's voice as input, and generates spoken audio in that speaker's voice. This is primarily for speech synthesis researchers and engineers developing new voice cloning or custom voice applications.
194 stars. No commits in the last 6 months.
Use this if you need to rapidly create new, distinct voices for text-to-speech from only a few seconds of example audio, especially for research into speaker-adaptive TTS.
Not ideal if you are looking for a ready-to-use application to generate voices without any coding or machine learning expertise, as this is a research implementation requiring significant setup.
Stars
194
Forks
37
Language
Python
License
—
Category
Last pushed
Jun 08, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/SungFeng-Huang/Meta-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