VoxCPM 1.5
VoxCPM1.5 is OpenBMB’s tokenizer-free TTS model that generates expressive, context-aware speech and realistic zero-shot voice clones in Chinese and English, with real-time streaming and open-source weights that support full and LoRA fine-tuning.
- Type
- Audio
- Weights
- Open
More from OpenBMB
11
-
38k DL
MiniCPM V4.6.
Multimodal
MiniCPM-V-4.6 is OpenBMB’s open-source lightweight multimodal model for efficient image, multi-image, and vid…
-
731k DL
MiniCPM-o 4.5
Multimodal
MiniCPM-o 4.5 is an on-device multimodal LLM (~9B params) that matches Gemini 2.5 Flash on vision and speech,…
-
339k DL
MiniCPM-o-2_6
Multimodal
any to any · License apache-2.0 · 338,737 downloads · by openbmb
-
139k DL
MiniCPM-V-4_5
Multimodal
image text to text · License apache-2.0 · 138,613 downloads · by openbmb
-
107k DL
MiniCPM-V-4.6-Thinking
Multimodal
image text to text · License apache-2.0 · 106,778 downloads · by openbmb
-
536k DL
MiniCPM5 1B
Text
MiniCPM5-1B is OpenBMB’s open-source 1B causal language model for on-device local assistants, coding agents,…
-
89k DL
MiniCPM5-1B-MLX
Text
text generation · License apache-2.0 · 89,020 downloads · by openbmb
-
767k DL
MiniCPM5-2B
Text
text generation · License apache-2.0 · 767,352 downloads · by openbmb
About OpenBMB
1
OpenBMB is short for Open Lab for Big Model Base. The goal of OpenBMB is to build the model base and toolkit for large-scale pre-trained language models.