# OpenBMB Releases VoxCPM2 for Expressive TTS

> The new diffusion-based model from the OpenBMB research group supports multilingual speech, emotional control, and zero-shot voice cloning.

Published by The Open Weights on Apr 3, 2026. Canonical: https://theopenweights.com/news/voxcpm2-1326

## Key facts

- Company: OpenBMB
- Model: VoxCPM2
- Version: 2
- Category: Text → Speech
- Modalities: Text → Speech
- License: Other (Open weights, commercial use allowed)
- Precision: BF16
- Weights size: 4.6 GB
- Languages: 30 languages
- Significance: notable
- Published: 2026-04-03
- Last verified: 2026-06-17
- Hugging Face: https://huggingface.co/openbmb/VoxCPM2
- Canonical URL: https://theopenweights.com/news/voxcpm2-1326

The OpenBMB research community has released VoxCPM2, a powerful new open-source model for text-to-speech synthesis. Built on a modern diffusion-based architecture, the model aims to generate high-fidelity, expressive human speech in multiple languages.

## Cloning and Control
VoxCPM2's standout feature is its ability to perform zero-shot voice cloning using just a 3-to-20 second audio sample of a target voice. This allows it to generate speech in a new voice without specific training. The model also offers fine-grained control over the output, with key capabilities including:

*   **Cross-lingual synthesis:** Generate speech in one language using a voice from another (e.g., speaking Chinese with an English speaker's vocal characteristics).
*   **Emotional control:** Adjust the emotional tone of the generated speech.
*   **Multilingual support:** Primarily trained on Chinese and English.

The model uses a two-stage cascaded diffusion process. The first stage converts text into a mel-spectrogram, an acoustic representation of the audio. A second-stage vocoder then converts this spectrogram into a final audio waveform, a technique known for producing high-quality results.

VoxCPM2 represents another significant step forward for open-source generative audio, providing capabilities that rival proprietary systems. It gives researchers and developers a powerful tool for creating custom voice applications. The model is available for download on the [Hugging Face Hub](https://huggingface.co/openbmb/VoxCPM2), though users should note its custom "OpenBMB Model License" for any usage considerations.

## Get the model

- [Hugging Face](https://huggingface.co/openbmb/VoxCPM2)

## Sources

- [openbmb/VoxCPM2](https://huggingface.co/openbmb/VoxCPM2) — Hugging Face, Apr 3, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "OpenBMB Releases VoxCPM2 for Expressive TTS", The Open Weights, Apr 3, 2026, https://theopenweights.com/news/voxcpm2-1326