ModelPrésentéExterne

VoxCPM1.5 GGUF

GGUF-converted weights of openbmb/VoxCPM1.5 for the C++/ggml engine llama.cpp-omni (tools/omni/voxcpm2). Runs VoxCPM1.5 TTS + voice cloning natively on CPU / Metal / CUDA / Vulkan — no PyTorch runtime required.

Sourcehuggingface.co/DennisHuang648/VoxCPM1.5-GGUF/tree/4b7295096e17ed85565b16028315b6863e21f91f

TypeOtherModèle de baseopenbmb/VoxCPM1.5VersionRevision 4b72950BClasse

Source du modèle

Type: Other
Taille du fichier: 519–974 MB
Modèle de base: openbmb/VoxCPM1.5
Version: vRevision 4b72950
Mis à jour: 25 sept. 2026
Téléchargements: 80
Source: Hugging Face

Description de la source

VoxCPM1.5 — GGUF weights for llama.cpp-omni

GGUF-converted weights of openbmb/VoxCPM1.5 for the C++/ggml engine 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

./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.

Sources

1 source

Hugging FacePrincipalVersion 4b7295096e17ed85565b16028315b6863e21f91f

huggingface.co/DennisHuang648/VoxCPM1.5-GGUF/tree/4b7295096e17ed85565b16028315b6863e21f91f

Vérifié 6 sept.

Artefacts du modèle

3 artefacts

VoxCPM-1.5-Acoustic-F16.gguf

gguf · 867 MB · SHA-256 6f81c7753bf1…feab · Hugging Face

Télécharger

VoxCPM-1.5-BaseLM-F16.gguf

gguf · 974 MB · SHA-256 79c57d8a62d1…2ba2 · Hugging Face

Télécharger

VoxCPM-1.5-BaseLM-Q8_0.gguf

gguf · 519 MB · SHA-256 ca48db71b418…fc94 · Hugging Face

Télécharger

Extraits de sources

2 extraits

Readme6 sept.huggingface.co/DennisHuang648/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.

Note6 sept.huggingface.co/DennisHuang648/VoxCPM1.5-GGUF

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