AuraScribe
Free, offline voice dictation for Windows, macOS & Linux
What it does
AuraScribe is free, open-source, 100% offline voice dictation for Windows, macOS, and Linux. Press a hotkey, speak, and clean punctuated text appears at your cursor in any app. Every word is transcribed on your own machine: no account, no subscription, no cloud. The only network request it ever makes is a one-time model download; after that it works fully offline. A private, local alternative to Wispr Flow, Superwhisper, and Dragon. MIT licensed, free forever.
Free, open-source voice dictation and voice typing, 100% offline on Windows, macOS and Linux. A private, free Wispr Flow alternative. Type by voice in any app.
Press a hotkey, talk, and clean, punctuated text lands in any app on Windows, macOS, and Linux. It is transcribed on your own machine and never sent to a server. Each engine detects the language itself inside its own region, so there is no picker to set and no round trip to a server. Download only the ones you actually speak. Download the installer for your system, set a hotkey, and start dictating in under a minute. No account to create, nothing to pay, and no cloud to trust with your voice. There is no window to open, no record button to find, and no upload waiting to finish. The whole loop happens where your hands already are. Hit Ctrl + Shift + Space (Cmd + Shift + Space on a Mac) in…from aurascribe.dev
Does the same job
all alternatives →
SpeakoFlowAug 2026 · speakoflow.com · ▲95Free, open-source voice dictation and AI assistant, offline
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com