YazSes

MSKazemi·MSKazemi.YazSes

Offline voice dictation — hold a key, speak, release. No cloud, no API key, no subscription.

YazSes is a free, open-source, offline voice dictation and speech-to-text tool. Hold a key, speak, release — your words are transcribed on your own CPU and typed into whatever window has focus. Everything runs on-device with faster-whisper. There is no cloud service, no API key, no account and no subscription, and no telemetry of any kind. Use it when audio must not be sent to a third party — a confidential meeting, an air-gapped machine, or simply a preference not to rent your own voice. It also transcribes recordings (`yazses transcribe talk.m4a`, with optional speaker labels) and can capture a whole meeting into a speaker-labelled transcript with locally generated minutes.

winget install --id MSKazemi.YazSes --exact --source winget

Latest 2.36.0·August 30, 2026

Release Notes

Installer type: inno

x64—6DE31B891D20BB35E531B0D47CB057B5B561920D9AE8140A95A2F50CF36B1204
arm64—187A31129F3102C3E06F81526FB19E7A3C804BC55D84D8D74DAF208DA2DF5C02

Details

Homepage
https://mskazemi.com/yazses/
License
Apache-2.0
Publisher
MSKazemi
Support
https://github.com/MSKazemi/yazses/issues
Copyright
Copyright 2026 Mohsen Seyedkazemi Ardebili
Moniker
yazses

Tags

voicedictationvoice-typingspeech-to-textspeech-recognitionwhispertranscriptionofflineon-deviceprivacyaccessibilityproductivityopen-source

Older versions (1)

2.35.0
x64—9D07AF8615F554DE3EE641FC4EF611378BBBE7F2F4AD382B5EB8786DF37A876C
arm64—DE85FF3E98DB88BCA8F2A2D69A09D317A2680D79D03504E76EDE7233E7C8FC64