yl4579/StarGANv2-VC
StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion
This project helps audio engineers, voice actors, and content creators change the voice characteristics in an audio recording without needing a script. You input an audio file with someone speaking, and it transforms the voice to sound like a different speaker or even adopt a specific emotional style or singing voice, producing a new audio file with the converted voice. It's designed for professionals working with spoken or sung audio who need flexible voice manipulation.
518 stars. No commits in the last 6 months.
Use this if you need to convert a voice in an audio recording to sound like another person or to adopt a specific stylistic attribute like emotion or singing, without requiring text transcriptions.
Not ideal if you need to generate speech from text (text-to-speech) or if you require extremely precise control over every phonetic detail of the converted voice.
Stars
518
Forks
111
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/StarGANv2-VC"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
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。
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