hcy71o/SNAC
Unofficial Pytorch implementation of SNAC: Speaker-normalized affine coupling layer in flow-based architecture for zero-shot multi-speaker text-to-speech
This project helps create realistic, human-like speech from written text, even for voices it hasn't heard before. You provide text and a small audio sample of a target voice, and it generates that text spoken in the new voice. This is ideal for content creators, educators, or anyone needing to produce custom voiceovers efficiently without hiring professional voice actors.
No commits in the last 6 months.
Use this if you need to generate high-quality, custom voice narration for text in a voice that sounds natural and consistent, even if you only have a short sample of that voice.
Not ideal if you're looking for a simple, off-the-shelf text-to-speech solution without custom voice generation capabilities, or if you need to generate speech in many different languages without specific voice cloning.
Stars
57
Forks
10
Language
Python
License
MIT
Category
Last pushed
Aug 07, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/hcy71o/SNAC"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
bshall/Tacotron
A PyTorch implementation of Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesis
Kyubyong/dc_tts
A TensorFlow Implementation of DC-TTS: yet another text-to-speech model
DemisEom/SpecAugment
A Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain
Rayhane-mamah/Tacotron-2
DeepMind's Tacotron-2 Tensorflow implementation
Kyubyong/tacotron
A TensorFlow Implementation of Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model