User repository on GitHub
Private Mac voice diary: local Parakeet transcription, Jev sorting, Notion library
- Forks
- 2
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
Capture
A private Mac voice diary: Parakeet transcribes your voice on-device, TypeSafe Jev splits each capture into separate thoughts and files them into Notion as notes, tasks and reminders, and nothing is saved until you approve it.
- Stars
- 3
- Language
- Dart
- License
- MIT
- Reading time
- 3 min
- Published by
- Community
- Author
- Abid A Gafoor
- Last verified
- Oct 2026
- Platforms
- macOS
- Capabilities
- Open sourceRuns locallyRequires API key
Highlights
- Press ⌃⌥ in any app to record; Parakeet transcribes on your Mac or iPhone and audio never goes to an AI service.
- Jev splits what you said into separate thoughts and files each one into your groups; titles and bodies come from your own words.
- Nothing reaches Notion until you press Yes, save, unless auto-save is turned on; approved tasks with a time become macOS notifications.
- First-run setup downloads a roughly 670 MB speech model, stores the TypeSafe key in the macOS Keychain, and creates Notion databases under a page you choose.
- Requires macOS 12 or later; releases are signed and notarised when signing secrets are set, and unsigned builds say so in their release notes.
Watch out
Grounded in the truncated repository README and GitHub metadata reviewed on 2026-10-15; the repo's language is Dart, which is not in this catalog's language list, so no language is claimed. The README was cut off in the use section, so behaviour around recording before setup finishes is not covered here.
Questions about this entry
Short answers drawn from the linked project or page.
A private Mac voice diary by Abid A Gafoor: press a shortcut, speak, and your thoughts land in Notion as notes, tasks and reminders, with captures and recordings saved under one Notion page you choose.
After local transcription, Jev splits what you said into separate thoughts and files each one into your groups. Titles and bodies come from your own words, so it sorts rather than rewrites, and you approve the result before saving.
No. Parakeet transcribes on your Mac or iPhone and, per the README, audio never goes to an AI service. Text is sent to Jev for sorting, and captures go to your own Notion workspace once you approve them.
macOS 12 or later, a TypeSafe API key and a Notion workspace. First-run setup downloads a speech model of roughly 670 MB, checked and resumable, then walks through the TypeSafe key and the Notion internal connection.
Download the latest DMG from GitHub Releases, open it and drag Capture into Applications. Releases are signed with a Developer ID and notarised by Apple once signing secrets are set; for an unsigned build, allow it under System Settings, Privacy & Security, Open Anyway.
The TypeSafe key is stored in the macOS Keychain. For Notion you create an internal connection, add it to one page, then paste the token and the page link; Capture creates its Groups, Captures and Library databases under that page.
Yes, with Settings, Save to Notion automatically: recordings save without the review card and a notification says what was saved. The card still appears when something needs a look, and approved tasks with a time become macOS reminders.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Voice-controlled computer use on a Mac
X: Speech to live slides
X: Jev for real-time speech
X: On-device audio, no LLM in the loop
More Jev resources like this
A Mac-only voice assistant: say Hey Jev or hold right Option and Jev decides every command in one call for $0.00004 per request, while Whisper transcribes locally, Fish Audio S2.1 Pro speaks replies, and an LLM wakes only for questions.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
henryklunaris/hey-jevPython
henryklunaris/hey-jevPythonA local app that reads a few lines of notes about your product and lets Jev pick its way to a finished landing page: Jev never writes text, it only chooses between options, and code builds the page from those picks.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
sagapranav/jev-pagesHTML
sagapranav/jev-pagesHTMLA voice-driven control layer for macOS: speak a goal and the Mac does it, watching the screen through the accessibility tree with everything running locally. Jev is the fallback, not the router — deterministic matching resolves commands in about 50 ms.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
coco-research/jev-useRust
coco-research/jev-useRustA native macOS utility that decides which listening ports are safe to stop: one Jev question per process turns a locally collected dossier into a typed verdict — stop, keep or your decision — with the evidence and the most material missing fact. Only you can confirm a stop.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
epiphany-dynamics/port-cleanupSwift
epiphany-dynamics/port-cleanupSwiftA schema-guided document-to-graph pipeline: local parsing feeds entity mentions and bounded candidate pairs to Jev, which chooses among closed-set relations, and every edge lands as proposed, review, or rejected with page-level evidence.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
chenmingtang830/jevgraphPython
chenmingtang830/jevgraphPythonA Chrome extension that autofills web forms from unstructured notes: paste your details as plain text once, and Jev matches each form field to the best line and fills it, never touching password or payment fields.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
imohitmayank/jevfillTypeScript
imohitmayank/jevfillTypeScriptFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.