OpenWhispr: Turn your voice into text with a hotkey
Added · Updated
Made by OpenWhispr
View profile on GitHub (opens in a new tab)OpenWhispr lets you press a hotkey, speak, and see your words typed at your cursor, for people who dictate, take notes or transcribe meetings.
What it does
OpenWhispr is a desktop app that turns speech into text. You can use speech-to-text models that run on your own device, such as Whisper and NVIDIA Parakeet, so audio never leaves it, or choose cloud processing for speed. It also records meetings, keeps notes, and offers a voice assistant.
How to use it
Download the app for macOS, Windows or Linux from the releases page linked in the project's documentation, then use the hotkey, speak, and your words are pasted into the app you are in. On macOS or x86 64 Linux, a community maintained Homebrew cask also exists.
Common use cases
- Dictate an email or chat message into any app: press the hotkey, speak, and the text pastes in automatically.
- Record a Zoom or Teams call and get a transcript with speaker labels, plus notes you can search.
- Drag in an audio or video file, or paste a YouTube link, to turn it into a text transcript.
Can I use this?
Requirements Download the installer for your platform. Local transcription runs models on your device; cloud processing and AI assistants such as GPT or Claude are optional alternatives. The quickstart docs cover platform specific steps.
Caveat With the assistant hotkey you can opt in to sending a screenshot of your current screen as context. Licensed under MIT.
Worth knowing On Intel Macs, live speaker identification and voice fingerprinting are unavailable, and notes search uses keyword matching instead of semantic search.
Why it's here
Not trending this week
Last seen on the GitHub trending list on 31 October 2026. It stays on BuildTube so you can still find it.
- 10,987 people have starred it on GitHub.
Numbers checked on 8 November 2026; not refreshed since.
Behind it
View setup guideBuildTube has not run or verified this project. Everything above is written from what the creator published.
Made this?
Quick questions
- What is OpenWhispr?
- OpenWhispr is a desktop app that turns speech into text.
- What can I use OpenWhispr for?
- Dictate an email or chat message into any app: press the hotkey, speak, and the text pastes in automatically; Record a Zoom or Teams call and get a transcript with speaker labels, plus notes you can search; Drag in an audio or video file, or paste a YouTube link, to turn it into a text transcript
- Can I run OpenWhispr on my computer?
- It installs as a desktop app on your own computer.
- What do I need to use OpenWhispr?
- A Mac, Windows or Linux computer with the app downloaded. Building from source requires Node.js 24+. Memory and GPU needs for local models are not documented.
- What license does OpenWhispr use?
- Licensed under MIT.
More from this week
- Handy Dictate into any text field with offline speech-to-text
Handy lets you press a shortcut, speak, and see your words appear in any text field, transcribed on your own computer.
- agent-desktop Let AI agents read and click desktop apps
For developers building computer-use agents: agent-desktop lets an AI agent read and operate desktop apps on Mac, Windows or Linux from a command line.
- Spec Kit Turn a written spec into plans, tasks and code
Spec Kit gives your AI coding agent a step-by-step process to build a feature, fix a bug or assess an idea.
Explore by topic
Post this
Download share imageFor makers
Made this? Show it’s on BuildTube — add the badge to your README or embed the card on your site.
README badge (Markdown)
[](https://buildtube.app/p/gh-openwhispr-openwhispr/)Embed card (HTML)
<iframe src="https://buildtube.app/embed/gh-openwhispr-openwhispr/" width="560" height="240" style="border:0;max-width:100%" loading="lazy" title="OpenWhispr on BuildTube"></iframe>