wukongrobot is a simple, flexible, and elegant Chinese voice dialogue robot/smart speaker project. It may also be the first open source smart speaker project that supports brain-computer interaction.
1. Modularity.
Functional plug-ins, speech recognition, speech synthesis, and conversational robots are all highly modularized. Third-party plug-ins are maintained separately, making it easy to inherit and develop your own plug-ins.
2. Chinese support.
It integrates Chinese speech recognition and speech synthesis technologies from Baidu, iFlytek, Alibaba, Tencent, etc., and can continue to be expanded.
3. Conversation robot support.
Supports local conversation robots based on AnyQ, and supports access to online conversation robots such as Turing robot and Emotibot.
4. Global monitoring and offline wake-up.
Supports Muse brain-computer wake-up and contactless offline voice command wake-up.
5. Flexible and configurable.
Supports customizing robot names and selecting plug-ins for speech recognition and synthesis.
6. Smart home.
Supports linkage with smart home protocols such as mqtt and HomeAssistant, and supports voice control of smart home appliances.
7. Backend supporting support.
A supporting backend is provided to enable functions such as remote control, configuration modification, and log viewing.
8. Open API.
You can use the open API on the back end to achieve richer functions.
9. Easy to install and supports more platforms.
Compared with dingdang-robot, PocketSphinx's offline wake-up solution is abandoned, making the installation simpler, with less code, easier to maintain, and can run on Mac and more Linux systems.
Python
wukong-robot only supports Python 3.5+ and does not support Python 2.x.
wukong-robot supports running on the following devices and systems
64bitMacOSX
64bit Ubuntu (12.04 and 14.04)
Full range of Raspberry Pi (Raspbian system)
Pine 64 with Debian Jessie 8.5 (3.10.102)
Intel Edison with Ubilinux (Debian Wheezy 7.8)
Windows with WSL (Windows Subsystem for Linux) installed