OpenWhisper
Desktop dictation and meeting-notes app with optional Jev fast judgments for citation checks, history search and live meeting cues.
Overview
OpenWhisper is a desktop app for Windows, macOS and Linux covering dictation with a global hotkey, audio-file transcription and meeting notes, using local speech models or the OpenAI API, with optional AI cleanup, personal dictionaries, snippets, per-app tone, voice command mode, history search and export. Meeting Mode captures microphone and system audio with a live dashboard, AI insights and a live copilot.
An optional Fast judgments feature uses TypeSafe (or an existing OpenRouter key) to add citation checks, meaning-based history search and live meeting cues. Per the list summary, Jev checks cover topic changes, note-taker instructions and sensitive text. It is MIT licensed and available as packaged releases or from source.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Yes / no | Has the meeting topic changed? | yes · no |
| Yes / no | Is this an instruction to the note-taker? | yes · no |
| Yes / no | Does this text contain sensitive information? | yes · no |
How it works
- Transcribe meeting audio live.
- With Fast judgments on, ask Jev typed questions about segments.
- Show cues, check citations and flag sensitive text.
- Use meaning-based search over history.
Strengths
- Optional; core app works without it.
- Works with a TypeSafe or OpenRouter key.
- Local transcription option.
Caveats
- Fast judgments send text to the decision provider.
- Linux system audio is a preview.
Getting started
Download a packaged release from GitHub, then enable Meeting Mode > Fast judgments with a TypeSafe or OpenRouter key.At a glance
- Type
- Model
- Status
- production
- Language
- Python
- Runtime
- desktop app
- Has code
- yes
- License
- MIT
Use cases and integrations
How curated lists describe it
A dictation and meeting-notes app with optional Jev checks for topic changes, note-taker instructions and sensitive text.
logicrw/awesome-jev-projects
Frequently asked questions
Where is Jev used?
In optional Fast judgments for citation checks, history search and live meeting cues.
Do I need TypeSafe?
No, Fast judgments are optional and can use an OpenRouter key.
Does it run locally?
Transcription can use local speech models.
Related projects
Fills Japanese government PDF forms by asking Jev which profile item each unlabeled field is; personal values stay in the browser.
ServicebetaJavaScriptMCP server and Claude Code plugin that files each captured note with one Jev request deciding kind, project, action and duplicates.
PluginprototypeTypeScriptLocal-first meeting transcription and conversation memory app whose live voice path runs its evaluations through Jev.
AppbetaRustPublic Jev playground showing a scheduling Choice with an explicit Unresolved option to separate mentioned times from agreed meeting times.
AppOpen-source AI email assistant; listed as using Jev as an optional classifier for email intent and triage.
ProjectproductionTypeScriptChrome extension that groups and orders all tabs in a window by meaning and your rules with a single Jev request.
ServiceproductionTypeScript