Last updated
Private, offline speech-to-text and dictation for Windows, powered by the open-source OpenASR engine -- no cloud, no telemetry, fully local.
$ winget install --id Caelum.OpenASRDesktop --exact --version 0.1.8Run in Command Prompt, PowerShell, or Windows Terminal. Prompts for any agreements.
OpenASR Desktop uses EXE (NSIS). The silent install switches are /S.
OpenASR-Desktop-0.1.8-x64-setup.exe /S
For Intune admins
Automated application patching for Microsoft Intune. Pckgr keeps a curated library of 1,000+ apps continuously up-to-date in your tenant via Microsoft Graph - no manual repackaging, no chasing vendor sites.
Start free 30-day trialNo credit card required.
OpenASR Desktop brings system-wide dictation and audio/meeting transcription to Windows, running entirely on-device on top of the Apache-2.0 OpenASR speech-recognition engine (ggml-backed, eleven model families, CPU and GPU inference). Nothing is uploaded: no cloud fallback, no telemetry, no account required. Models are downloaded once from a signed catalog and then run fully offline.
| Architecture | Type | Scope | Install | Download |
|---|---|---|---|---|
| x64 | EXE NSIS | user | Direct |
Copy a command tailored to that specific architecture, type, and scope - useful when winget would otherwise pick a different default.
No known CVEs for OpenASR Desktop.
Coverage is best-effort and depends on a winget package mapping to an NVD CPE entry. Absence here is not a guarantee of safety.
More from Caelum Inc. or browse speech-recognition, speech-to-text, transcription.