openbmb / text-to-speech updated 3 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

900 K

Likes

1,516

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

Download history

daily snapshots · 10 days

1.0 M899 K

Jul 28Jul 31Aug 3Aug 6

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

Kokoro-82M 12.0 M XTTS-v2 9.2 M chatterbox 2.5 M Qwen3-TTS-12Hz-1.7B-CustomVoice 2.3 M Kokoro-82M-v1.0-ONNX 1.4 M F5-TTS 770 K

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB