# How VoxCPM Leverages the MiniCPM-4 Backbone for Speech Generation

> Discover how VoxCPM system uses the MiniCPM-4 backbone for advanced speech generation. Explore its powerful text-to-speech capabilities.

- Repository: [OpenBMB/VoxCPM](https://github.com/OpenBMB/VoxCPM)
- Tags: deep-dive
- Published: 2026-04-10

---

**VoxCPM is a multimodal speech-generation system that uses MiniCPM-4, a 2B-parameter open-source transformer, as its core language model backbone to power text-to-speech capabilities.**

The relationship between VoxCPM and the MiniCPM-4 backbone is foundational to the architecture of this open-source audio generation system. Located in the `OpenBMB/VoxCPM` repository, VoxCPM imports the complete MiniCPM-4 implementation to serve as the textual understanding engine, combining it with specialized audio