OmniVoice-GGUF

GGUF weights for [omnivoice.cpp](https://github.com/ServeurpersoCom/omnivoice.cpp), a C++17/GGML port of OmniVoice (k2-fsa/OmniVoice). Multilingual zero shot TTS, 646 languages, 24 kHz mono. Runs on CPU, CUDA, ROCm, Metal, Vulkan. Two GGUFs load together : omnivoice-base-{variant}.gguf Qwen3 0.6B backbone, text -> tokens omnivoice-tokenizer-{variant}.gguf HuBERT + DAC + RVQ, tokens <-> 24 kHz audio git clone --recurse-submodules https://github.com/ServeurpersoCom/omnivoice.cpp.git cd omnivoice.cpp && ./buildcuda.sh mkdir -p models huggingface-cli download Serveurperso/OmniVoice-GGUF \ omnivoice-base-Q8_0.gguf omnivoice-tokenizer-Q8_0.gguf \ --local-dir models cd examples ./tts.sh # voice design -> tts.wav ./clone.sh # voice cloning -> clone.wav Set `GGML_BACKEND` to force a device, otherwise the runtime picks the best one available. Tokenizer GGUFs are not uniform quants. Three categories get a dedicated treatment : Same fallback as llama.cpp `tensor_type_fallback` : F16 has no block size and matches the runtime target dtype on every backend. The base LM (Qwen3 0.6B, hidden = 1024) has all dimensions divisible by 256 so the fallback never triggers, the LM follows standard llama.cpp K-quant across variants. Upstream model : OmniVoice by Xiaomi / k2-fsa, Apache 2.0 Audio codec : Higgs Audio v2 (bosonai/higgs-audio-v2-tokenizer), Apache 2.0 GGUF tooling : omnivoice.cpp, MIT