OpenASR

Free plan APILinuxMacSelf-hostedWindows

What OpenASR is

OpenASR converts speech into text on your own computer for recordings, dictation, and live captions. Its desktop app can transcribe files, enter dictation into other apps, and display captions as you speak. It can also distinguish speakers and attach timestamps to transcript text, with exports available as plain text, structured data, or timestamped subtitles. You can select models from a catalog; the models run on your machine, and transcription can continue offline.

OpenASR says audio, models, and transcripts stay local, with no account, telemetry, analytics SDK, or cloud transcription route. Optional refinement or translation sends recognized text to the provider you select. Desktop versions are available for Apple Silicon Macs and Windows 10 or later on x64. The public Apache-2.0 open core includes a CLI, local HTTP API, model format, and Docker server, with Linux support for the CLI and server; the local API implements part of the OpenAI audio transcription API. The desktop apps are closed source, and a native Linux desktop app is planned. OpenASR Desktop is free.

Who it suits

OpenASR suits people who want local, offline transcription for recordings, dictation, or captions, and developers who need a local CLI or server. It is also a fit for users who want speaker labels, timestamps, and multiple export formats, provided their desktop runs macOS on Apple Silicon or Windows 10 or later on x64.

What it does well

Transcription can continue without an internet connection.
Supports file transcription, app dictation, and live captions.
Separates speakers and pairs transcript text with timestamps.
Exports plain text, structured data, and timestamped subtitles.
Open core is public under Apache-2.0.

What to know first

Native Linux desktop app is planned, not available yet.
First-use model download is roughly 1 GB.
Installed model packs stay on disk until removed.
macOS and Windows desktop apps are closed source.

Limits

OpenASR Desktop is free. The first-use model download is roughly 1 GB, and installed model packs remain on disk until removed.

Plans

Plan	Billed and limits	Price
OpenASR Desktop	Free to start; macOS and Windows desktop apps; Linux desktop app planned	Free

As openasr.org lists them, read 10 Oct 2026. The maker's own page has the final word.

Getting started

Visit https://openasr.org/ to get started.
Choose the desktop app for Apple Silicon Mac or Windows 10 or later on x64, or use the CLI or server on Linux.
Select a model from the model catalog and allow for the roughly 1 GB first-use download.
Use the desktop app for files, dictation, or captions, or connect through the local HTTP API.

Verdict

Choose OpenASR if local processing and offline transcription matter, or if you need its CLI and local server. Look elsewhere if you need a native Linux desktop app or require every part of the software to be open source.

Questions

Is OpenASR free?

OpenASR Desktop is free. The listed pricing model is free, and it has a free plan.

Does OpenASR work offline?

Yes. Audio, models, and transcripts are processed locally, and transcription can continue without a network connection.

Which desktop platforms are supported?

The desktop apps support Apple Silicon Macs and Windows 10 or later on x64. A native Linux desktop app is planned; the CLI and server support Linux.

Is OpenASR open source?

The Rust core, CLI, local HTTP API, and model catalog are public under Apache-2.0. The macOS and Windows desktop apps are closed source.

Does it send data to a cloud transcription service?

OpenASR says it has no cloud transcription path. Optional text refinement or translation sends recognized text to the provider you select.

Facts from OpenASR's own pages

API compatibility: The local server supports a subset of the OpenAI audio transcriptions API, and the docs say existing integrations can usually point to its local server URL. · openasr.org, 10 Oct 2026
Desktop platforms: The desktop apps are available for Apple Silicon Macs and Windows 10 or later on x64; a native Linux desktop app is planned. · openasr.org, 10 Oct 2026
Developer tools: The open core includes a CLI, local HTTP API, model format, and Docker server, with CLI and server support for Linux. · openasr.org, 10 Oct 2026
Exports: The site lists plain text, structured data, and timestamped subtitles as export formats. · openasr.org, 10 Oct 2026
Local processing: Audio, models, and transcripts are processed locally, and transcription can continue without a network connection. · openasr.org, 10 Oct 2026
Models: Users can choose from a model catalog, and the site says models run on the user’s own machine. · openasr.org, 10 Oct 2026
Notable limit: The troubleshooting page says the default first-use model download is roughly 1 GB and each installed model pack remains on disk until removed. · openasr.org, 10 Oct 2026
Offline dictation: Yes · openasr.org, 20 Sept 2026
Privacy: The product says it has no telemetry, analytics SDK, account, or cloud transcription path; optional text refinement or translation sends recognized text to the selected provider. · openasr.org, 10 Oct 2026
Privacy model: on-device · openasr.org, 20 Sept 2026
Product: OpenASR turns speech into text on a user’s computer for recordings, dictation, and live captions. · openasr.org, 10 Oct 2026
Project status: The Rust core, CLI, local HTTP API, and model catalog are public under Apache-2.0, while the macOS and Windows desktop apps are closed source. · openasr.org, 10 Oct 2026
Security: The site says model downloads are verified and describes a signed model catalog; macOS downloads are signed and notarized, and the Windows installer is signed. · openasr.org, 10 Oct 2026
Speaker and timestamps: OpenASR can separate speakers and keep timestamps beside transcript text. · openasr.org, 10 Oct 2026
Support: The troubleshooting page directs users who remain stuck to open an issue on GitHub with their operating system details and steps tried. · openasr.org, 10 Oct 2026
Supported platforms: macOS,Windows,Linux (CLI/server) · openasr.org, 20 Sept 2026
Transcription features: The desktop app supports file transcription, dictation into other apps, and live captions. · openasr.org, 10 Oct 2026