Mr.Speech
Don’t just transcribe Turn conversations into organized work
What it does
Mr.Speech is a local-first desktop voice workspace that connects dictation, meetings, notes, plans, and AI. Speak into any app, capture meetings with speaker identification, organize conversations by project, ask questions with evidence, turn action items into structured work, and expose that context to MCP-compatible assistants like ChatGPT, Claude, or Cursor. Available on macOS, Windows, and Linux.
Mr.Speech turns your voice into finished work on macOS, Linux, and Windows. Dictate into any app, turn meetings into decisions and tasks, keep AI notes. With a fully private on-device mode; cloud optional, processed in Europe.
Mr.Speech is the connected voice workspace. Dictate into any app on your desktop, turn meetings into decisions and tasks, and keep an AI notebook that ChatGPT and Claude can read and write. With a fully private mode that never touches the internet. Fillers gone. Punctuation placed. And because you're in an email window, it writes like an email. Mr.Speech formats for the app you're in, automatically. Mr.Speech types directly into your focused window, including your inbox, code editor, terminal, or chat app. No window switching, no copy-paste, and your clipboard is untouched. A sentence you speak in a meeting becomes a task with an owner and a due date. Same app, zero copy-paste. A global…from mrspeech.app
Does the same job
all alternatives →
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 · 17d 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 · 27d 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 · 17d ago · simedw.com