PrivaSpeech

What it does

Speech-to-text that never leaves your machine. PrivaSpeech runs 100% locally on Windows. It is powered by NVIDIA's Parakeet V3, works offline, no internet required. Your voice data stays on your device, period. No PHI transmission, no cloud processing, no BAA paperwork. Unlike Dragon or Windows Dictation, there's nothing to trust but your own hardware. Global hotkey, instant clipboard paste, runs on CPU or GPU. Built for anyone who takes data ownership seriously. Try it free for a month.

Private speech-to-text for Windows and macOS. Transcribe on your device and paste into any app. Dictate offline after activation and the model download.

PrivaSpeech is a local speech-to-text app for Windows and macOS. Record your voice, transcribe on your device, and paste the text into any app. Dictation works offline after activation and the model download. Press Ctrl+Space anywhere. Speak. Press again. Your text lands in the clipboard. Dictation audio stays on your machine. No cloud transcription. After activation and the model download, dictation works offline. No cloud transcription API required. Tuned for modern CPUs. Light footprint, fast startup, no extra hardware. Transcription happens entirely on your hardware. Temporary audio is cleared the moment it's no longer needed. Never uploaded, never logged. After a one-time setup,…from privaspeech.com

• 
  WhisperstreamAug 2026 · whisperstream.io · ▲77

  Local AI dictation for Windows

• 
  DictatoFeb 2026 · dicta.to · ▲93

  I built a macOS dictation app where everything runs on-device. Transcription, auto-correct, translation. No audio or text leaves your machine. It ships with 4 transcription engines you can swap between: WhisperKit (99 languages), NVIDIA Parakeet TDT 0.6B (25 European languages, fastest of the bunch), Qwen3-ASR 0.6B (30 languages), and Apple Speech on macOS 26+. They all run through CoreML/Metal. Whisper is the most versatile, Parakeet wins on raw latency for European languages, Qwen3 does better with CJK. I went with a protocol-based architecture so you pick the engine that fits your…

• 
  SaylineJan 2026 · sayline.app · ▲83

  I built a voice dictation app for macOS mostly because I was tired of how awful Siri is and I didn't want to pay a subscription for cloud tools. The app uses NVIDIA's Parakeet v3 (TDT) as the primary engine. Inference is handled by the FluidAudio library. It's insanely fast on M-series chips. For Intel users, I added local Whisper support ranging from Tiny up to Large v3 Turbo (quantized to save space). The interesting part was the AI integration. I originally tried to pipeline the ASR output into Apple's Intelligence Foundation Model. It was a nightmare, because the content moderation…

• 
  SpeakoFlowAug 2026 · speakoflow.com · ▲95

  Free, open-source voice dictation and AI assistant, offline

• 
  VoiceGeckoAug 2026 · voicegecko.dev · ▲102

  Open source, local voice-to-text

• 
  Chirp – Local Windows dictation with ParakeetV3 no executable requiredNov 2025 · github.com · ▲34

  I’ve been working in fairly locked‑down Windows environments where I’m allowed to run Python, but not install or launch new `.exe` files. In addition the built-in windows dictations are blocked (the only good one isn't local anyway). At the same time, I really wanted accurate, fast dictation without sending audio to a cloud service, and without needing a GPU. Most speech‑to‑text setups I tried either required special launchers, GPU access, or were awkward to run day‑to‑day. To scratch that itch, I built Chirp, a Windows dictation app that runs fully locally, uses NVIDIA’s ParakeetV3 model,…

• 
  Lofi Cities – Pixel-art city nights with browser-generated lofi▲319

  Endless lofi beats composed live in your browser, over pixel-art nights in Paris, Tokyo, New York, Hong Kong, Sydney, San Francisco and more. Free, no sign-up.

  Work · 26d ago · loficities.com

• 
  Smooth Recorder▲257

  Mac screen recordings that look edited when you hit stop

  Work · 20d ago · smoothrecorder.com

• 
  Figma Specs▲225

  A container for your context that lives on the Figma canvas

  Work · 5d ago · figma.com

• 
  The rarest tech books and docs you've probably never read▲190

  Work · 14d ago · readrare.com

• GP
  Gemini Pro 3 imagines the HN front page 10 years from now▲3,346

  Life & fun · Dec 2025 · dosaygo-studio.github.io

• 
  Jmail – Google Suite for Epstein files▲1,557

  Hi everyone! My name's Luke and I made the original Jmail here alongside Riley Walz. We had a ton of friends collaborate on building out more of the app suite last night in lieue of DOJ's "Epstein files" release. Please AMA!

  Life & fun · Dec 2025 · jmail.world

• 
  Loki.Build▲743

  Design and ship studio-grade landing pages with AI

  AI · Dec 2025 · loki.build

• 
  PlanEat AI▲733

  AI turns your health goals into a 7-day menu & grocery list

  AI · Dec 2025 · planeatai.com

• 
  22 GB of Hacker News in SQLite▲730

  Community, All the HN belong to you. This is an archive of hacker news that fits in your browser. When I made HN Made of Primes I realized I could probably do this offline sqlite/wasm thing with the whole GBs of archive. The whole dataset. So I tried it, and this is it. Have Hacker News on your device. Go to this repo (https://github.com/DOSAYGO-STUDIO/HackerBook): you can download it. Big Query -> ETL -> npx serve docs - that's it. 20 years of HN arguments and beauty, can be yours forever. So they'll never die. Ever. It's the unkillable static archive of HN and it's…

  Dev tools · Dec 2025 · hackerbook.dosaygo.com

• 
  CyberCut AI▲723

  AI video studio for viral social clips

  AI · Dec 2025 · cybercut.ai