jackaduma/CycleGAN-VC2
Voice Conversion by CycleGAN (语音克隆/语音转换): CycleGAN-VC2
This project helps convert a spoken audio recording from one person's voice into another person's voice without needing them to say the same phrases. You provide audio samples of the original speaker and the target speaker, and it produces an audio file where the original speech is delivered in the target speaker's voice. This is useful for content creators, voice actors, or anyone needing to change the vocal identity of recorded speech.
571 stars. No commits in the last 6 months.
Use this if you need to transform spoken audio to sound like a different speaker, even if you don't have parallel recordings (i.e., the same script spoken by both individuals).
Not ideal if you need to generate entirely new speech from text in a specific voice, as this tool focuses on converting existing audio.
Stars
571
Forks
109
Language
Python
License
MIT
Category
Last pushed
Jun 10, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/jackaduma/CycleGAN-VC2"
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