moonbox-dev/VoxCPM2-GGUF

text-to-speech model by moonbox-dev

Open original source ↗

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

GGUF builds of VoxCPM2, made by Moonbox for on-device use with llama.cpp (Metal, CUDA, Vulkan, CPU). Every file is at the root of this repository: one model file per precision, plus the mmproj-.gguf file that holds the model's encoder (audio, vision or codec) when it has one. That file is shared by every precision. Pick a precision by the memory you have. The last column is the benchmark: the task score of each file on Moonbox's evaluation set for this kind of model (details under How to run), and how often it gives exactly the same output as the BF16 file. The BF16 file holds the original weights unchanged. Experimental: every file here is below Moonbox's quality bar on Chinese voice cloning. On English these files match the original. On Chinese, speaker similarity is 0.84-0.87 against the original's 0.91 in the same mode. The BF16 file holds the original weights…

moonbox-dev/VoxCPM2-GGUF on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-11-22T08:29:13.014Z

Inside the original model card — Document outline
  1. VoxCPM2 GGUF
  2. Files
  3. How to run
  4. How these were made
  5. License
  6. VoxCPM2
  7. Highlights
  8. Quick Start
  9. Installation
  10. Text-to-Speech
  11. Voice Design
  12. Controllable Voice Cloning

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the model card

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

moonbox-dev/VoxCPM2-GGUF is a text-to-speech model repository published by moonbox-dev on Hugging Face. The source reports the gguf library.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task
text-to-speech
Library
gguf
Recent downloads (30 days)
0
Cumulative likes
0
Hugging Face trending score
0
Reported safetensors parameters
Not reported
Architecture
Not reported
License
apache-2.0
Access
Not gated by Hugging Face
Created
2026-11-22T06:23:48.000Z
Last modified
2026-11-22T06:29:49.000Z

Compatibility and lineage

Language coverage was not reported.

Reported base models: openbmb/VoxCPM2

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-11-22T07:03:33.420Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related models

hexgrad/Kokoro-82M

audio-cpp/audio.cpp-gguf

coqui/XTTS-v2

k2-fsa/OmniVoice

ResembleAI/chatterbox

pnnbao-ump/VieNeu-TTS-v3-Turbo