VoxCPM2-GGUF

GGUF-converted weights of [openbmb/VoxCPM2](https://huggingface.co/openbmb/VoxCPM2) for the C++/ggml inference engine [llama.cpp-omni](https://github.com/tc-mb/llama.cpp-omni) (`tools/omni/voxcpm2`). These let you run VoxCPM2 text-to-speech and zero-shot voice cloning **natively on CPU / Metal / CUDA / Vulkan** via ggml — no PyTorch runtime required. VoxCPM2 outputs 48 kHz mono audio. You need one BaseLM (F16 or Q8_0) + the Acoustic file. Q8_0 halves the BaseLM download size with negligible quality loss and a slight speed boost. git clone https://github.com/tc-mb/llama.cpp-omni.git cd llama.cpp-omni cmake -B build -DCMAKE_BUILD_TYPE=Release cmake --build build --target voxcpm2-cli -j cmake -B build -DCMAKE_BUILD_TYPE=Release -DGGML_CUDA=ON cmake --build build --target voxcpm2-cli -j cmake -B build -DCMAKE_BUILD_TYPE=Release -DGGML_VULKAN=ON cmake --build build --target voxcpm2-cli -j cmake -B build -DCMAKE_BUILD_TYPE=Release cmake --build build --target voxcpm2-cli -j You need one BaseLM (F16 or Q8_0) + the Acoustic file. huggingface-cli download DennisHuang648/VoxCPM2- VoxCPM2-BaseLM-Q8_0.gguf VoxCPM2-Acoustic-F16.gguf \ --local-dir ./models huggingface-cli download DennisHuang648/VoxCPM2-GGUF \ VoxCPM2-BaseLM-F16.gguf VoxCPM2-Acoustic-F16 --local-dir ./models Build `voxcpm2-cli` from llama.cpp-omni, then: ./voxcpm2-cli \ -t "Hello, this is VoxCPM2 running through llama.cpp-omni." \ -o output.wav \ VoxCPM2-BaseLM-F16.gguf \ VoxCPM2-Acoustic-F16.gguf ./voxcpm2-cli -t "Cloned voice." -r speaker.wav -o clone.wav \ VoxCPM2-BaseLM-F16.gguf VoxCPM2-Acoustic-F16.gguf ./voxcpm2-cli -t "Target text." --prompt-wav speaker.wav --prompt-text "transcript of speaker.wav" \ -o clone.wav VoxCPM2-BaseLM-F16.gguf VoxCPM2-Acoustic-F16.gguf Key flags: `--cfg` (guidance scale, default 2.0), `--timesteps` (CFM steps, default 10), `--seed`, `--temperature`, `--stream`. Voice design: prefix the text with `(a calm female voice)…`. Produced with the official converter against the upstream PyTorch weights: python tools/omni/voxcpm2/convert_voxcpm2_to_gguf.py \ --model model.safetensors \ --vae audiovae.pth \ --config config.json \ --output ./out Weights derive from [openbmb/VoxCPM2](https://huggingface.co/openbmb/VoxCPM2); their original license/terms apply. Conversion tooling and inference engine: [llama.cpp-omni](https://github.com/tc-mb/llama.cpp-omni).