JMS1717/ming-voice
Low-latency local speech-to-speech voice assistant with Ming-3.0-audio-tiny on AMD Radeon GPUs (ROCm on WSL2)
- Stars
- 285
- Forks
- 14
- Open issues
- 0
- Last push
- 2d ago
About ming-voice
ming-voice is a free, open-source LLM chat app by JMS1717, written mainly in Python. Low-latency local speech-to-speech voice assistant with Ming-3.0-audio-tiny on AMD Radeon GPUs (ROCm on WSL2). It has 285 GitHub stars and 14 forks, and was last updated 2d ago. It's released under the MIT license, a standard open-source license.
- License
- MIT
- Commercial use
- Commercial OK
- Language
- Python
- Stars
- 285
- Last update
- 2d ago
- Runs on Mac
- Not stated
- GPU
- Not stated
- Paid API key
- Not required
- Self-hostable
- Not stated
Similar free tools
speech-to-speech14k stars · Build voice agents with open-source models
openclaw393k stars · Runs AI assistants on your devices for personal or team use.
leon18k stars · An open-source personal AI assistant for local tasks and automation.
Open-LLM-VTuber14k stars · Create a voice-interactive AI companion with a Live2D avatar.
local-deep-research9.4k stars · AI research assistant for deep, agentic research using local LLMs and search engines.
Vane38k stars · Privacy-focused AI-powered answering engine with local and cloud LLM support.
ming-voice FAQ
Can I use ming-voice commercially?
Yes. MIT is a permissive license: commercial use is allowed as long as you keep the license notice. This is a plain-English summary, not legal advice.
Is ming-voice free?
Yes. ming-voice is open source and free to use. It's released under the MIT license, a standard open-source license.
Does ming-voice run on a Mac?
The project doesn't say. Check its installation guide before you start.
Does ming-voice need a GPU?
The project doesn't state hardware needs. AI models generally run much faster with a GPU.
Is ming-voice still maintained?
Yes. It was last updated 2d ago and has 0 open issues on GitHub.
What are alternatives to ming-voice?
Similar free, open-source tools include speech-to-speech, openclaw, leon, Open-LLM-VTuber.