candlewill/AiVoice
Deep CNN networks for Speech Synthesis
This project helps developers create a single-speaker text-to-speech system. You provide text sentences and audio recordings from a single speaker, and the system learns to convert new text into spoken audio in that speaker's voice. This is primarily used by engineers or researchers working on speech synthesis technology.
No commits in the last 6 months.
Use this if you are a developer or researcher looking to experiment with or build a text-to-speech system for a single speaker.
Not ideal if you need an out-of-the-box solution for generating speech without any programming or machine learning expertise.
Stars
49
Forks
15
Language
Python
License
—
Category
Last pushed
Nov 15, 2017
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/candlewill/AiVoice"
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)