OpenASR
openasr.org
- Free plan
- Windows
- macOS
- Linux
- API
- Self-hosted
What OpenASR is
OpenASR turns speech into text on a computer for recordings, dictation, and live captions. Audio, models, and transcripts stay local, so transcription can continue without a network connection. The product says it has no telemetry, analytics SDK, account, or cloud transcription path; optional refinement or translation sends recognized text to the selected provider. Desktop features include file transcription, dictation into other applications, live captions, speaker separation, and timestamps. Exports include plain text, structured data, and timestamped subtitles. Users choose models from a catalog that runs on their own machine. Desktop apps support Apple Silicon Macs and Windows 10 or later on x64; a native Linux desktop app is planned. The Apache-2.0 open core includes a CLI, local HTTP API, model format, and Docker server, with Linux CLI and server support. The local server supports part of the OpenAI audio transcriptions API. OpenASR Desktop costs nothing.
Who it suits
It suits users who need offline transcription, dictation, or captions while keeping processing on their own computers. Developers can use the local CLI, HTTP API, model format, or Docker server.
Good to know, and what to watch
- Local processing and offline transcription
- No telemetry, account, or cloud transcription path
- Speaker separation and transcript timestamps
- Plain text, structured, and subtitle exports
- Open-source CLI and local server
- First-use model download is roughly 1 GB
- Installed model packs remain until removed
- Native Linux desktop app is planned
- Desktop apps are closed source
Plans
Every plan and priceOpenASR Desktop
Open source
The verdict
OpenASR focuses on local speech recognition with desktop workflows and developer interfaces. Its offline privacy model is clear, but users should account for model storage and current desktop-platform coverage.
What the maker publishes
- 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. source
- 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. source
- Developer tools
- The open core includes a CLI, local HTTP API, model format, and Docker server, with CLI and server support for Linux. source
- Exports
- The site lists plain text, structured data, and timestamped subtitles as export formats. source
- Local processing
- Audio, models, and transcripts are processed locally, and transcription can continue without a network connection. source
- Models
- Users can choose from a model catalog, and the site says models run on the user’s own machine. source
- 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. source
- Offline dictation
- Yes source
- 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. source
- Privacy model
- on-device source
- Product
- OpenASR turns speech into text on a user’s computer for recordings, dictation, and live captions. source
- 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. source
- 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. source
- Speaker and timestamps
- OpenASR can separate speakers and keep timestamps beside transcript text. source
- Support
- The troubleshooting page directs users who remain stuck to open an issue on GitHub with their operating system details and steps tried. source
- Supported platforms
- macOS,Windows,Linux (CLI/server) source
- Transcription features
- The desktop app supports file transcription, dictation into other apps, and live captions. source
Checked against the maker's pages on 10 Oct 2026.