yl4579/StyleTTS
Official Implementation of StyleTTS
This project helps creators, educators, and businesses generate highly natural and emotionally expressive voiceovers from text. You provide written text and a short sample of reference speech, and it outputs synthesized audio that matches the desired speaking style, prosody, and emotional tone of the reference. Anyone who needs to produce realistic, nuanced synthetic speech for audio content, virtual assistants, or educational materials would find this useful.
462 stars. No commits in the last 6 months.
Use this if you need to create speech that sounds incredibly human, with consistent speaking styles and emotional tones, from written text.
Not ideal if you only need basic, monotone text-to-speech without specific style or emotional nuance, or if you don't have reference audio to guide the style.
Stars
462
Forks
68
Language
Python
License
MIT
Category
Last pushed
Jan 13, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/yl4579/StyleTTS"
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