OpenBMB/VoxCPM
tokenizer-free text-to-speech system
This repository provides a tokenizer-free text-to-speech system that directly generates continuous speech representations via an end-to-end diffusion autoregressive architecture. By bypassing discrete tokenization, it enables highly natural and expressive synthesis for multilingual speech generation, creative voice design, and voice cloning.
- Stars
- 37,900
- Stars gained in 7 days
- +200
- Contributors
- 28
- Forks
- 4,300
- Days trending in the last 30
- 1 days
- Mark
- Watch — 1,354 stars per contributor. An automatic mark on public metrics: above 500 is watch, above 2,000 possible hype (not a judgement of quality).