QuickCapture - Scan & Speak
The only receipt scanner with offline voice notes
What it does
Every receipt scanner lets you scan. QuickCapture lets you SPEAK. Scan a receipt, then instantly add voice context that transcribes offline: "Gas for Atlanta business trip, 14.2 gallons at Shell." No typing while driving. No forgetting details later. Built for gig workers, delivery drivers, and anyone tracking expenses for taxes. Your voice notes become searchable text alongside OCR data. Everything works 100% offline for privacy (Premium enables Google Drive backup optionally).
Does a similar job
all alternatives →- OVOffline voice messages transcription in Signal Desktop2022 · a2p.it · ▲191
- SASpeech and Audio To Text – Transcribe voice messages offline2025 · apps.apple.com · ▲6
Hi HN, I’d like to share a side project I recently finished: Speech & Audio To Text, a small iOS utility to transcribe voice messages from apps like WhatsApp, Telegram, and Voice Memos — fully offline and without sending any data to the cloud. The motivation was personal. I often receive voice notes when I can't listen to them — during meetings, while commuting on noisy trains, or when I don’t want to disturb others. I used to rely on an app that handled this well, until it moved to a subscription model and started requiring constant internet access. I wanted something that would: - Work…
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 · 18d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d 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, November 2025
the whole month →
- IB
Life & fun · Nov 2025 · bitsnpieces.dev
- BBoing▲782
Life & fun · Nov 2025 · boing.greg.technology