Transcrio
Record and transcribe any audio on your Mac. No meeting bot.
What it does
Transcrio is a local-first macOS recorder for calls, lectures, voice notes, and any audio playing on your Mac. It captures microphone + system audio without a meeting bot, platform integration, or organizer permissions, saves source audio and generated text files on your Mac, and turns recordings into transcripts and summaries. When processing is needed, Transcrio handles recordings temporarily and does not keep your audio, transcripts, or summaries.
Does the same job
all alternatives →
- TOTrace – Offline Mac meeting transcripts you can flag mid-callJun 2026 · traceapp.info · ▲205
I'm the developer of Trace, a non-intrusive, shortcut-driven Mac app that records and transcribes your meetings on-device. I know, another meeting transcription app. Please bear with me though, I'm confident that this is at least a little novel. I primarily built Trace for myself. I'd been using MacWhisper, but there was enough fiddling before each call that I'd forget to start it and walk out of an hour-long meeting with nothing written down. So the things I cared about most were that it's quick to activate and stays out of the way. You activate Trace by pressing a global shortcut…
- RTRM2000 Tape Recorder, an audio sampler for macOS2025 · rm2000.app · ▲63
RM2000 Tape Recorder makes it stupid simple to grab audio samples and organize them: just record the sample, give it a title (and maybe some tags), and it is saved neatly into a directory of your choosing. I'm a huge datahoarder and have always appreciated tools / services like PureRef and Are.na which help me make sense of everything I collect. Those services concern themselves with images and video - I wondered, why can't the same be done with music and audiofiles? I actually got the inspiration for the filenaming scheme from the Emacs Denote package - every sample is saved in the…
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, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com