Model reference · open weights
VoxCPM2 is an open-weight audio or speech model from openbmb, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
VoxCPM2 VoxCPM2 is a tokenizer-free, diffusion autoregressive Text-to-Speech model — 2B parameters, 30 languages, 48kHz audio output, trained on over 2 million hours of multilingual speech data. [](https://github.com/OpenBMB/VoxCPM) [](https://voxcpm.readthedocs.io/en/latest/) [](https://huggingface.co/spaces/OpenBMB/VoxCPM-Demo) [](https://openbmb.github.io/voxcpm2-demopage) [](https://discord.gg/KZUx7tVNwz) [](https://applink.feishu.cn/client/chat/chatter/addbylink?linktoken=acds0b9d-23d8-4d7e-b696-d200f3e22a7f) [](https://modelbest.feishu.cn/wiki/UtWxwcERfiRIpIkBOjuc3h9tn1D) Highlights - 🌍 30-Language Multilingual — No language tag needed; input text in any supported language directly - 🎨 Voice Design — Generate a novel voice from a natural-language description alone (gender, age, tone, emotion, pace…); no reference audio required - 🎛️ Controllable Cloning — Clone any voice from a short clip, with optional style guidance to steer emotion, pace, and expression while preserving timbre - 🎙️ Ultimate Cloning — Provide reference audio + its transcript for audio-continuation cloning; every vocal nuance faithfully reproduced - 🔊 48kHz Studio-Quality Output — Accepts 16kHz reference; outputs 48kHz via AudioVAE V2's built-in super-resolution, no external upsampler needed - 🧠 Context-Aware Synthesis — Automatically infers appropriate prosody and expressiveness from text content - ⚡ Real-Time Streaming — RTF as low as ~0.3 on NVIDIA RTX 4090, and ~0.13 accelerated by Nano-VLLM - 📜 Fully Open-Source & Commercial-Ready — Apache-2.0 license, free for commercial use Arabic, Burmese, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Indonesian, Italian, Japanese, Khmer, Korean, Lao, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Tagalog, Thai, Turkish, Vietnamese Chinese Dialects: 四川话, 粤语, 吴语, 东北话, 河南话, 陕西话, 山东话, 天津话, 闽南话 Quick Start Installation Requirements: Python ≥ 3.10, PyTorch ≥ 2.5.0, CUDA ≥ 12.0 · Full Quick Start → Text-to-Speech Voice Design Put the voice description in parentheses at the start of text, followed by the content to synthesize: Controllable Voice Cloning Ultimate Cloning Provide both the referen
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | openbmb |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 2.3B |
| Variants | 1 |
| Runs with | voxcpm |
| Released | 2026-04-03 |
| Popularity | 330k downloads / month |
| Likes | 1,558 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| VoxCPM2 | 2.3B | BF16 | ~5.3 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys voxcpm2 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (voxcpm2 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="voxcpm2" -F file=@audio.mp3
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗