maum-ai/wavegrad2
Unofficial Pytorch Implementation of WaveGrad2
This project helps generate natural-sounding speech from written text. You provide text, like sentences or paragraphs, and it produces an audio file of that text being spoken. This is useful for content creators, educators, or anyone needing high-quality voiceovers without human recording.
112 stars. No commits in the last 6 months.
Use this if you need to convert written English or Mandarin text into high-quality spoken audio for various applications.
Not ideal if you require real-time speech synthesis for interactive applications, or if you need to generate speech in languages other than English or Mandarin.
Stars
112
Forks
16
Language
Jupyter Notebook
License
BSD-3-Clause
Category
Last pushed
Aug 18, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/maum-ai/wavegrad2"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
descriptinc/descript-audio-codec
State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz...
drethage/speech-denoising-wavenet
A neural network for end-to-end speech denoising
YuanGongND/ast
Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".
iver56/torch-audiomentations
Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.
lmnt-com/wavegrad
A fast, high-quality neural vocoder.