andi611/Conditional-SpecGAN-Tensorflow
Text-to-Speech Synthesis by Generating Spectrograms using Generative Adversarial Network
This project helps audio engineers and researchers generate human-like speech from text. You input raw text, and it produces an audio waveform that sounds like a person speaking. It's designed for those who need to synthesize high-quality speech for various applications.
No commits in the last 6 months.
Use this if you need to transform written text into natural-sounding spoken audio.
Not ideal if you're looking for a simple, ready-to-use text-to-speech application without deep learning setup.
Stars
10
Forks
6
Language
Python
License
MIT
Category
Last pushed
Dec 12, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/andi611/Conditional-SpecGAN-Tensorflow"
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)