pritishyuvraj/Voice-Conversion-GAN
Voice Conversion using Cycle GAN's For Non-Parallel Data
This project helps audio engineers, voice artists, or content creators change the vocal characteristics of an audio recording without needing a matching performance from the target voice. You provide audio files from a source speaker and audio files from a target speaker, and it produces new audio where the source speaker's words are spoken in the target speaker's voice.
125 stars. No commits in the last 6 months.
Use this if you need to convert a speaker's voice in an audio recording to sound like another specific speaker, even if you don't have parallel recordings of both speakers saying the same things.
Not ideal if you're looking for real-time voice modulation or simply want to apply generic voice effects like pitch shifting or echo.
Stars
125
Forks
31
Language
Jupyter Notebook
License
Unlicense
Category
Last pushed
Dec 18, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/pritishyuvraj/Voice-Conversion-GAN"
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