yl4579/StyleTTS-VC
Official Implementation of StyleTTS-VC
This project helps audio content creators and developers quickly change the voice in an audio recording to match a target speaker, even with only a short sample of that target voice. You provide an existing audio recording and a single reference audio clip of the desired target voice, and it produces the original recording spoken in the target voice. This is ideal for sound engineers, voice actors, or game developers working on media production or character voicing.
197 stars. No commits in the last 6 months.
Use this if you need to transform spoken audio to a new voice using a minimal sample of the target voice, maintaining naturalness and similarity.
Not ideal if you need to convert text into speech (Text-to-Speech) or require highly specialized voice manipulation beyond changing identity.
Stars
197
Forks
28
Language
Python
License
MIT
Category
Last pushed
Jan 14, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/yl4579/StyleTTS-VC"
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