VoxCPM 1.5 Brings Open-Source Voice Cloning
The new 500-million-parameter text-to-speech model from OpenBMB supports both English and Chinese and can replicate a voice from a short audio sample.
The field of open-source text-to-speech has a new contender with the release of VoxCPM 1.5 by the OpenBMB research group. The model introduces high-quality, zero-shot voice cloning capabilities to the community, enabling users to generate speech in a specific voice using just a short audio sample.
Built on the MiniCPM-4 architecture, VoxCPM 1.5 is a compact 500-million-parameter model. Its relatively small size makes it more accessible for developers and researchers to run and fine-tune on a wider range of hardware, lowering the barrier to entry for creating custom speech applications.
Bilingual Voice Synthesis
A key advantage of the model is its bilingual nature, supporting both English and Chinese within a single framework. This, combined with its permissive Apache 2.0 license, makes it a versatile tool for global applications. Key features include:
- Zero-shot voice cloning from brief audio clips.
- Bilingual support for English and Chinese.
- An efficient 500M parameter architecture.
By providing an open and powerful tool for voice synthesis, OpenBMB is enabling new possibilities in areas like personalized digital assistants, accessible technology, and creative content generation. Developers can explore the model and its capabilities in the official Hugging Face repository.
Sources
- Visit
openbmb/VoxCPM1.5
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.