Rongjiehuang/ProDiff

PyTorch Implementation of ProDiff (ACM-MM'22) with a Extremely-Fast diffusion speech synthesis pipeline

44
/ 100
Emerging

This tool helps create high-quality, natural-sounding speech from written text quickly. You provide the text you want to be spoken, and it generates an audio file of that text being read aloud. This is ideal for content creators, educators, or businesses needing to convert scripts into spoken audio for various applications.

432 stars. No commits in the last 6 months.

Use this if you need to rapidly produce clear, high-fidelity spoken audio from text for commercial or personal use.

Not ideal if you require fine-grained control over vocal nuances like emotion, specific accents, or very unique voice characteristics beyond standard text-to-speech.

audio-production content-creation voice-over e-learning media-production
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

432

Forks

52

Language

Python

License

MIT

Last pushed

Apr 19, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Rongjiehuang/ProDiff"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.