shivammehta25/Matcha-TTS
[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
Matcha-TTS is for anyone who needs to convert written text into high-quality, natural-sounding spoken audio quickly. You provide the text you want spoken, and it generates the corresponding speech audio. This is ideal for content creators, educators, or businesses looking to automate narration or voiceovers.
1,259 stars.
Use this if you need to rapidly generate realistic speech from text for various applications, especially when speed and naturalness are critical.
Not ideal if you need highly customized voice modulation beyond speaking rate and temperature, or if you require fine-grained control over individual phonemes.
Stars
1,259
Forks
189
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Mar 09, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/shivammehta25/Matcha-TTS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
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。
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
shivammehta25/Neural-HMM
Neural HMMs are all you need (for high-quality attention-free TTS)