OpenBMB Releases VoxCPM for Open Voice Synthesis
The new 500-million-parameter model offers high-quality text-to-speech and zero-shot voice cloning under a permissive license.
The OpenBMB research collective has released VoxCPM-0.5B, a new open-source model for speech generation. At just 500 million parameters, it's designed to be a relatively lightweight yet capable tool for developers working with synthetic audio. The model is available under a permissive Apache 2.0 license, encouraging broad adoption.
VoxCPM is built upon the architecture of the MiniCPM model family, specifically drawing from the multimodal capabilities of MiniCPM4. By extending this foundation into the audio domain, OpenBMB provides a high-quality speech synthesis model that is both accessible and efficient, continuing the trend of powerful, specialized open models in smaller weight classes.
Zero-Shot Voice Cloning
The model's primary strength lies in its ability to perform zero-shot voice cloning. This means it can replicate a person's voice from a short audio sample without requiring any specialized fine-tuning or retraining. Its core features include:
- Bilingual text-to-speech in English and Chinese.
- Zero-shot voice cloning from brief audio clips.
- High-quality, natural-sounding audio output.
For researchers and developers interested in exploring its capabilities, the model is available for download on Hugging Face. Its open license and modest size make it a compelling option for projects requiring custom voice generation or real-time speech synthesis applications.
Sources
- Visit
openbmb/VoxCPM-0.5B
Hugging Face
More from OpenBMB
All OpenBMB releases →
OpenBMB's MiniCPM-OCR 1.0 Targets Document Parsing
A compact vision-language model built to read tables, formulas, and complex page layouts arrives on Hugging Face.
OpenBMB's MiniCPM-V 4.7 brings MoE to vision models
The new 35B-parameter vision-language model activates just 3B parameters per pass, aiming for efficiency without sacrificing capability.
MiniCPM-V 4.7 brings a 35B MoE vision model on-device
OpenBMB's latest multimodal release activates just 3B parameters per token, aiming to keep capable image understanding local.
More in Text → Speech
All Text → Speech →
Liquid AI's LFM3-Omni-2B brings any-to-any AI to the edge
The 2-billion-parameter model combines vision, audio and speech-to-speech in a package small enough to run on device.
IBM's Granite Switch 4.1 Unifies Chat, Logic, Speech
A single endpoint now routes text conversation, decision-making, and speech synthesis across IBM's Apache-licensed Granite line.
Fish Audio's Drama 3 brings MoE to open TTS
The open-source speech model pairs a 35B mixture-of-experts backbone with voice cloning and directed performance control.
0 comments
No comments yet. Be the first to weigh in.