openbmb/VoxCPM2

Text To Speech·openbmb· 635.8K· 1.5K

voxcpm apache-2.0 2.3B params

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.

Open in MLForge Sign up free Desktop app Source ↗

# pull & run locally
pip install mlforge-sdk && mlforge pull openbmb/VoxCPM2

Model details

Task

Text To Speech

Provider

openbmb

Framework

voxcpm

Parameters

2.3B

Size

8.9 GB

License

apache-2.0

Downloads

635.8K

Likes

1.5K

Paper

arXiv:2509.24650

Updated

2026-04-16

About openbmb/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.

Related Text To Speech

K hexgrad/Kokoro-82M Text To Speech 15.5M 6.4K 🤗 HF X coqui/XTTS-v2 Text To Speech 9.2M 3.6K 🤗 HF C ResembleAI/chatterbox Text To Speech 2.2M 1.7K 🤗 HF Q Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice Text To Speech ·1.9B params 2.0M 1.6K 🤗 HF Q Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice Text To Speech ·905.8M params 1.2M 163 🤗 HF O k2-fsa/OmniVoice Text To Speech ·612.6M params 1.0M 1.1K 🤗 HF