openbmb / text-to-speech Open weights updated 2 months ago

VoxCPM2

Name: VoxCPM2
Author: openbmb

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.

Params

2.3 B

Context

—

Downloads 30d

902 K

Likes

1,710

Commercial use: allowed apache-2.0 Not gated SAFETENSORS 30 languages View on Hugging Face ↗

Download history

daily snapshots · 87 days

▲ 516 K in the last 30 days (133.9%)

1.0 M350 K

Jul 28Aug 26Sep 24Oct 22

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	4.6 GB	5.9 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Parameters: 2.3 B
Tensor type: BF16
Licence: apache-2.0
First seen on the Hub: 2026-04-03
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with any text-to-speech model

Popular comparisons

audio.cpp-gguf 6.6 M XTTS-v2 6.3 M Qwen3-TTS-12Hz-1.7B-CustomVoice 2.0 M OmniVoice 1.9 M chatterbox 1.8 M F5-TTS 887 K

Appears in

Best open-source TTS