VoxCPM1.5 GGUF

--- license: apache-2.0 base_model: openbmb/VoxCPM1.5 tags: - text-to-speech - tts - voice-cloning - gguf - llama.cpp - voxcpm language: - zh - en library_name: gguf --- # VoxCPM1.5 — GGUF weights for llama.cpp-omni GGUF-converted weights of [openbmb/VoxCPM1.5](https://huggingface.co/openbmb/VoxCPM1.5) for the C++/ggml engine [llama.cpp-omni](https://github.com/tc-mb/llama.cpp-omni) (`tools/omni/voxcpm2`). Runs VoxCPM1.5 TTS + voice cloning natively on CPU / Metal / CUDA / Vulkan — no PyTorch runtime required. ## Files | File | Format | Size | Component | |------|--------|------|-----------| | `VoxCPM-1.5-BaseLM-F16.gguf` | F16 | ~974 MB | Base language model | | `VoxCPM-1.5-BaseLM-Q8_0.gguf` | Q8_0 | ~519 MB | Base language model, 8-bit (recommended) | | `VoxCPM-1.5-Acoustic-F16.gguf` | F16 | ~867 MB | Acoustic stack (ResidualLM + FSQ + CFM + AudioVAE) | Output: **44.1 kHz mono**. Use one BaseLM (Q8_0 recommended) + the Acoustic file. ## Usage ```bash ./voxcpm2-cli -t "Hello from VoxCPM 1.5." -o out.wav \ VoxCPM-1.5-BaseLM-Q8_0.gguf VoxCPM-1.5-Acoustic-F16.gguf # voice cloning: add -r speaker.wav ``` Verified on Apple M4 Pro / Metal (RTF ~1.68). Flags: `--cfg`, `--timesteps`, `--seed`, `--temperature`, `-r` (clone), `--prompt-wav`/`--prompt-text` (reference-transcript clone), `--cpu`. License/terms inherit from the upstream model.

Source context: 80 downloads · 0 likes · Pipeline text-to-speech · Library gguf · Repo DennisHuang648/VoxCPM1.5-GGUF