hcy71o/SNAC

Unofficial Pytorch implementation of SNAC: Speaker-normalized affine coupling layer in flow-based architecture for zero-shot multi-speaker text-to-speech

40
/ 100
Emerging

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.

voice-synthesis audio-production content-creation narration media-localization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

57

Forks

10

Language

Python

License

MIT

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.