Appgithub-com-serveurpersocom-omnivoice-cpp

Download Pinokio

Sign in Create accountJoin

Sign in Create accountJoin

omnivoice.cpp

github.com/ServeurpersoCom/omnivoice.cppUpdated 5mo ago

Repository details

Updated 2026-04-30T21:55:27.000Z

Indexed 2026-05-02T04:04:12.990Z

Local AI text-to-speech with voice cloning and voice design, powered by GGML. C++17 port of OmniVoice (k2-fsa/OmniVoice). 646 languages, 24 kHz mono output, runs on CPU, CUDA, ROCm, Metal, Vulkan.

Loading community details…

Community

Sort by

Post about omnivoice.cpp...Post

Loading...

Loading project activity…

Pinokio

Pinokio Apps Using This Repo

No Pinokio apps using this repo yet.

Community tagsNone yet.

Check-ins (0)

Platforms (0)

No reports yet.

Arch (0)

No reports yet.

GPU (0)

No reports yet.

RAM (0)

No reports yet.

VRAM (0)

No reports yet.

Recent commits

ggml: reset submodule to upstream master, replay 3 clean commits

Pascal5 months agoc314519

ggml: fix MATH_LIBRARY check on Windows MSVC

Pascal5 months agobcd5179

ggml: rebase custom ops onto upstream HEAD

Pascal5 months ago2fea4e9

Pascal5 months ago2c8d600

quantize: F16 fallback for non-alignable conv weights, exclude snake alpha

Pascal5 months ago12ba749

tests: cross-decode WAV check uses stft_cos like the other probes

Pascal5 months agoa37671e

quant: protect RVQ + route compute through scheduler

Pascal5 months ago4aae7e4

examples : switch all scripts to Q8_0 codec, no audible difference

Pascal5 months ago07be385

fix : ARM cross-platform, cast conv weights to F16 at load time

Pascal5 months agoee88c9d

Pascal5 months ago510a046