Back to repositories
OpenBMBVoxCPM

VoxCPM: open source worth watching

A tokenizer-free multilingual text-to-speech system for natural speech, voice design, and controllable cloning.

Why we are featuring it

Synthetic speech that does not start from discrete tokens.

VoxCPM generates continuous speech representations through a diffusion autoregressive architecture. VoxCPM2 combines languages, voice design, cloning, and 48kHz audio in a model usable through Python and compatible serving options.

What is inside

  • The 2B-parameter VoxCPM2 model supports 30 languages.
  • Voice design from a natural-language description.
  • Controllable and ultimate cloning from reference audio.
  • 48kHz output and real-time streaming with vLLM options.
VoxCPM | Trending Repo | DevOP