talat is the local transcription app for meetings, dictation, and recordings: an AI note-taker that captures both sides of every conversation and transcribes in real time, entirely on your own computer. Nothing you say is ever uploaded.
VoiceTra - NICT
VoiceTra is a speech translation app that translates your speech into different languages.
Introducing Whisper – an open source voice note taking app! Record voice notes and transcribe them into lists, blogs, & more with AI. 100% free & open source. https://t.co/UZWGkUDJ6d
Introducing Whisper – an open source voice note taking app!Record voice notes and transcribe them into lists, blogs, & more with AI.100% free & open source. pic.twitter.com/UZWGkUDJ6d— Hassan (@nutlope) July 22, 2025
Razberry on Twitter / X
introducing Oat - a tiny meeting recorder for your macnotetakers like granola are overkill. i wanted something to record & transcribe meetings locally, and then save a markdown file to my machine so Claude/Codex can do the rest. no signups & free. bring your own agent… pic.twitter.com/lDlFlZeDcp— Razberry (@RazberryChai) September 3, 2026
turantekin/Parrot
Meeting recorder for your Mac with a live AI copilot. On-device transcription, answers from your own docs mid-call. Local-first and open source.
Launching a free, open-source, on-device transcription app
TL;DR – Please try Moonshine Note Taker on your Mac! For years I’ve been telling people that AI wants to be local, that on-device models aren’t just a poor man’s alternative…
BetterWispr: local dictation for macOS
Hold a shortcut, speak, and BetterWispr types clean text into any Mac app. Local speech models, a style for each app, meeting notes and insights. Free and open source, with no account required.
ChatGPT Voice can keep talking while it works - Sensemaker
OpenAI’s GPT-Live splits live conversation from slower search, reasoning, and agent work in the background.
Pebble Index 01
A smart ring that records voice notes at the press of a button and transcribes them to your phone. External memory for your brain.
Tin Can - The Landline, Reinvented for Kids
The super-magical Wi-Fi landline for kids. No screens, no texting, no strangers — just real conversation with Grandma, besties, and contacts you approve. Plug in, twirl that cord, and time-travel to pure voice fun.
Adding a feature because ChatGPT incorrectly thinks it exists | Holovaty.com
At Soundslice, our sheet music scanner digitizes music from photographs, so you can listen, edit and practice. We continually improve the system, and I keep an eye on the error logs to see which images are getting poor results.
Announcing transcribe.cpp
Meet transcribe.cpp, a new open-source C/C++ speech-to-text inference library with portable, GPU-accelerated support for multiple STT models. Developed through Mozilla.ai's Builders in Residence program, it makes adding fast, local transcription to applications easier than ever.
A shared lexicon for *video notes*? Looking for input before I build
I’m considering tobuild an app for recording short screen videos and sharing them as video notes. Basically Loom for AT. I’d love your input on the lexicon shape before I settle it. The use case You record your screen (a window, a region or the whole display) with your voice and an optional webcam bubble, and share it as a quick explanation, similar to post-it notes or voice memos. I see two main user groups: people working together who might send each other video notes (a bug walkthrough, de...
Scribe — Meeting notes that never leave your Mac
Scribe records, transcribes and summarises your meetings on your Mac. Free and open source.
Introducing **transcribe.cpp** 🎙️ A new open-source C/C++ speech-to-text inference library for fast, local transcription. ✅ Multiple GGUF STT models ✅ GPU acceleration (Metal, Vulkan & CUDA) ✅ Portable across platforms Built through @mozilla.ai's BiR program. Blog: blog.mozilla.ai/announcing-transcribe-cpp/
Announcing transcribe.cpp
blog.mozilla.ai