Pithflow
Hold a key, speak, get structured text in any Windows app
What it does
Most dictation tools hand you a transcript. Pithflow hands you finished text. Hold your hotkey, talk, let go — polished text lands in Slack, Gmail, VS Code, any Windows app. Cleanup strips the ums, fixes punctuation, applies your tone. • Windows-native, not an Electron port • Works over Citrix and RDP — nothing installs in the remote session • Bilingual EN/ES, Spanglish included, detected per dictation • Vocabulary packs for medical, legal, engineering terms Free tier, no card. Pro $9.99/mo.
AI voice dictation for Windows that works inside Citrix and Remote Desktop — nothing installs on the remote side. Hold a key, speak, get clean text.
Talk instead of typing. Pithflow turns your voice into clean, ready-to-send text — in Word, Outlook, Slack, Discord, or any app. No integration required. Pithflow types directly into the focused text field of any app. Click any tone and watch the message rewrite. Eight tones in the app, six shown here. Speech is messy. Writing is clean. Pithflow types the polished version of what you meant to say — fillers gone, punctuation right, tone yours. "um, so like, I guess maybe we should, uh, ship the thing on Friday, you know? if that works" Press and hold your hotkey, talk naturally, release. Cleaned text appears in any app — Slack, Gmail, VS Code, your browser. Processing starts the moment you…from pithflow.com
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 · 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 · 9d 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