#72 · Primary category： Speech & Audio
wukong-robot
🤖 wukong-robot is a simple, flexible, and elegant Chinese voice dialogue robot/smart speaker project, supporting ChatGPT multi-turn conversation, and possibly the first open-source smart speaker project to support brain-computer interaction.
Project last updated：10/25/24
GitHub Stars
7.1K
Forks
1.4K
Contributors
23
License
MIT
Why we included this project
This project is a good fit for anyone who wants to build a Chinese-speaking voice assistant on a Raspberry Pi or another small board without assembling the speech stack from scratch. It handles the whole pipeline: offline wake-word detection through Porcupine or Snowboy, pluggable speech recognition and synthesis from providers such as Baidu, iFlytek, OpenAI Whisper and Microsoft Edge, and TTS voice cloning. For dialogue it can use a local AnyQ instance or an online ChatGPT backend for multi-turn conversation, and it can connect to Home Assistant and MQTT so you can control smart-home gear by voice. The plugin system keeps the core clean while letting you add your own skills, which matters when you want a customized assistant rather than another off-the-shelf smart speaker. A Muse brain-computer wake option is a quirky experimental extra for anyone curious about hands-free control.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
whisper.cpp
Port of OpenAI's Whisper model in C/C++
Real-Time-Voice-Cloning
Clone a voice in 5 seconds to generate arbitrary speech in real-time
VibeVoice
Open-Source Frontier Voice AI
voicebox
The open-source AI voice studio. Clone, dictate, create.
TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production