Any-to-Any
Transformers
ONNX
Safetensors
English
Chinese
multimodal
audio
video
speech
streaming
full-duplex
long-video
custom-code
Instructions to use inclusionAI/Realtime-Venus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use inclusionAI/Realtime-Venus with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("inclusionAI/Realtime-Venus", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download Realtime-Venus-Audio/NOTICE from inclusionAI/Realtime-Venus: direct link, hf CLI and curl.
- Browser
- Download file 364 Bytes
-
https://huggingface.co/inclusionAI/Realtime-Venus/resolve/1b66c69ecb211de1e17845173a4567a41a9dbda2/Realtime-Venus-Audio/NOTICE
- Command line
-
hf download hf://inclusionAI/Realtime-Venus@1b66c69ecb211de1e17845173a4567a41a9dbda2/Realtime-Venus-Audio/NOTICE
-
curl -L -o NOTICE https://huggingface.co/inclusionAI/Realtime-Venus/resolve/1b66c69ecb211de1e17845173a4567a41a9dbda2/Realtime-Venus-Audio/NOTICE
364 Bytes
| Realtime-Venus-Audio | |
| Copyright 2026 The Realtime-Venus Team. All rights reserved. | |
| This product includes software derived from MiniCPM-o 4.5 | |
| (https://github.com/OpenBMB/MiniCPM-o), Copyright The OpenBMB Team, | |
| licensed under the Apache License, Version 2.0. | |
| Modifications focus on audio-only understanding and full-duplex speech | |
| conversation without visual input. | |