keonlee9420/WaveGrad2
PyTorch Implementation of Google Brain's WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis
This project helps you create natural-sounding spoken audio from written text. You provide text, and it generates speech recordings, allowing you to control the speaking rate. This is ideal for content creators, educators, or anyone needing to convert written material into audio.
No commits in the last 6 months.
Use this if you need to generate high-quality, human-like voiceovers directly from text, with the flexibility to adjust the speaking pace.
Not ideal if you need to generate voices in multiple languages or want to clone specific speaker voices from very limited audio samples.
Stars
69
Forks
18
Language
Python
License
MIT
Category
Last pushed
Aug 03, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/keonlee9420/WaveGrad2"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
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)