Drop in a recording
Meetings, interviews, lectures, voice memos — drop one in and go. Pick a model, click once, your Mac handles the rest. Edit the transcript inline or export it as subtitles.
OpenASR Desktop
your voice, your hardware.
OpenASR turns speech into text on your own computer — macOS and Windows today, Linux next. Drop in a file, dictate into any app, or run live captions. No account, no cloud, no upload.
Now on macOS and Windows
Audio stays on your computer No account required Built for the desktop
Say it. It’s written.
From voice to text
Meetings, interviews, classes, or passing ideas—OpenASR turns them into text on your computer, without an upload or a learning curve.
Made for everyday speech
Three waysto turn speech into text
No setup maze and no command line. Open the app and choose what you want to transcribe.
Type with your voice
Start dictating and words land right where your cursor is. Emails, notes, outlines — just talk. Punctuation is added for you.
See live captions
Online lectures, video calls, podcasts in another language — turn on captions and follow along. A floating overlay scrolls in real time. Nothing to install on the other end.
Beyond transcription
From heardto handled.
Models, audio, and results stay on your computer. Once the words appear, they are ready to review, organize, and export.
Your audio stays on your computer.
Audio, models, and transcripts are processed locally. Keep working even when the network is not.
Runs fully on your deviceNo audio uploaded
The model is your choice.
Go lighter for a quick response or choose a larger model for demanding audio. Download once, switch anytime.
Who said what, already separated. (Coming soon)
Keep different speakers distinct in meetings, interviews, and live captions.
Time and words stay together.
Keep timestamps beside the transcript so every line retains its place in the recording.
Take the result in the format you need.
Continue in plain text, structured data, or timestamped subtitles.
Every transcript is easy to find again.
Return to recent files, models, formats, and results without starting over.
One shortcut. Start talking.
Begin dictating without leaving the app you are already using.
Quickstart
Up and running in a minute.
The desktop app is the easiest path. The CLI is the same open-source engine, scriptable from a terminal.
- 1
Download & open
Download the desktop app for your platform and follow the short onboarding.
- 2
Pick a model
Onboarding suggests a recommended default — swap it any time from the Models screen, one click away.
- 3
Transcribe anything
Drop in a file, dictate straight into any app, or caption system audio live — all on-device.
Private by default
Your audio has no reason to leave.
Transcription runs on your own computer. There is no account, telemetry, or hidden cloud transcription path.
See exactly how privacy works For developers
Need the engine, not the app?
The CLI, local API, model format, and everything that touches audio remain available in the open core.
Has OpenASR helped you?
A GitHub Star helps more people discover private, local speech-to-text.
Support OpenASR on GitHub Start free · No account · No audio upload by default 
Local speech-to-text, on your computer.
No sign-up. No keys. No cloud. Just an app — and an open core you can read.
Download the desktop app