vibevoice

Unfortunate naming given I named my repo which does open source locally running speech to text vibevoice 7 months ago: https://github.com/mpaepper/vibevoice

I thought the name sounded familiar, I'm guessing its no relation to this project which has been around for 7 months? https://github.com/mpaepper/vibevoice

I built Vibevoice, a tool that lets you dictate text and run voice commands with screen context anywhere on your system. It works like this: For regular dictation, hold the right Ctrl key while speaking, then release to have your words typed automatically wherever your cursor is - perfect for coding, emails, or chat apps. The more interesting feature is the AI command mode: hold the Scroll Lock key, speak a prompt, and a local LLM responds based on both your words AND a screenshot of what you're looking at. The AI's response gets typed directly into your application as if you typed it yourself. Everything runs locally using Whisper for transcription and Ollama for the LLM (I recommend gemma3:27b for best results). No cloud services or API costs. The tool was inspired by Karpathy's "vibe coding" and builds upon Vlad's whisper-keyboard proj

Hello hackernews crew :) IInspired by Andrej Karpathy's recent post about vibe coding (https://x.com/karpathy/status/1886192184808149383) I built that functionality as a Python app. He mentioned he was using SuperWhisper, but that was only available for Mac and I am mainly using Ubuntu, so I hacked around to get a similar experience. It's a python script which runs faster-whisper locally on your GPU (or CPU, but then it's slower). Anywhere on your system, you can press the trigger button (defaults to the right Ctrl button), then speak some text and it will be immediately typed. So it works in any application - your IDE, your browser, your terminal, you name it. Check it out and let me know what you think: https://github.com/mpaepper/vibevoice I also added some more details and a quick video of how it works in this blog post: https://www.p