azraelkuan/FFTNet
FFTNet: a Real-Time Speaker-Dependent Neural Vocoder
This project helps generate realistic, human-like speech from existing audio recordings, making a speaker's voice "sing" new words. It takes processed audio features (like pitch and volume) from a single speaker's voice and outputs high-quality, real-time synthesized speech in that speaker's unique style. Voice-over artists, content creators, or anyone needing to create custom spoken audio from a specific voice could use this.
No commits in the last 6 months.
Use this if you need to create new speech utterances in a specific person's voice, particularly for applications requiring real-time audio generation.
Not ideal if you need to synthesize speech from text without a pre-existing audio training set from a specific speaker, or if you require a multi-speaker system.
Stars
64
Forks
10
Language
Python
License
—
Category
Last pushed
Aug 07, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/azraelkuan/FFTNet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
kan-bayashi/ParallelWaveGAN
Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch
fatchord/WaveRNN
WaveRNN Vocoder + TTS
shangeth/wavencoder
WavEncoder is a Python library for encoding audio signals, transforms for audio augmentation,...
rishikksh20/iSTFTNet-pytorch
iSTFTNet : Fast and Lightweight Mel-spectrogram Vocoder Incorporating Inverse Short-time Fourier...
seungwonpark/melgan
MelGAN vocoder (compatible with NVIDIA/tacotron2)