nafiuny/ICRCycleGAN-VC
Non-parallel voice conversion called ICRCycleGAN-VC based on CycleGAN and Inception-resNet module by Afiuny
This project helps audio engineers, voice artists, or content creators change the voice characteristics of a speaker in an audio recording without needing the speaker to re-record anything. You provide audio files from two different speakers, and it converts the voice in one recording to sound like the other speaker while preserving the original speech content. It's particularly effective for English and Persian speech.
Use this if you need to perform voice conversion between two speakers using existing audio, without requiring parallel recordings (where both speakers say the exact same phrases).
Not ideal if you need to generate speech from text (text-to-speech) or if you only have a single speaker's voice and want to create multiple new voices.
Stars
15
Forks
1
Language
Python
License
MIT
Category
Last pushed
Oct 30, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/nafiuny/ICRCycleGAN-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