rishikksh20/TFGAN
TFGAN: Time and Frequency Domain Based Generative Adversarial Network for High-fidelity Speech Synthesis
This project helps audio engineers, voice artists, or content creators generate extremely realistic, high-fidelity speech from text or existing audio patterns. You provide a dataset of speech recordings (like a voice actor's lines), and it produces synthesized speech that is difficult to distinguish from real human speech. It's ideal for anyone needing to create natural-sounding voiceovers, virtual assistants, or synthetic voices.
No commits in the last 6 months.
Use this if you need to generate very natural, high-quality synthetic speech for applications like voiceovers, virtual assistants, or realistic character voices.
Not ideal if you're looking for a simple text-to-speech converter for basic applications or if you don't have access to a substantial dataset of high-quality speech recordings for training.
Stars
88
Forks
19
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 23, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/rishikksh20/TFGAN"
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)