YazSes icon
YazSes icon

YazSes

Offline hold-to-talk voice dictation and transcription for the desktop. Hold a key, speak, release — the text is typed into the focused app. Speech recognition runs locally after setup and model download, so no cloud account, API key, GPU or subscription is needed.

YazSes screenshot 1

Cost / License

Application type

Platforms

  • Linux  Primary platform; works on X11 and Wayland. Hold-to-talk reads /dev/input, so the user must be in the "input" group. Wayland text injection needs ydotoold running.
  • Mac  Supported, but less extensively validated on real hardware than Linux. Requires granting Accessibility and Microphone permissions.
  • Windows  Supported, but less extensively validated on real hardware than Linux. The installer is currently unsigned.
YazSes screenshot 1
YazSes screenshot 2
YazSes alternatives  
0likes
8alternatives
0articles

Features

Properties

  1.  Privacy focused

Features

  1.  Voice dictation
  2.  Speech to text
  3.  Dictation

 Tags

YazSes News & Activities

Highlights All activities

Recent activities

YazSes information

AlternativeTo Categories

Audio & Music, OS & Utilities

GitHub repository

  •  4 Stars
  •  8 Forks
  •  162 Open Issues
  •   Updated  
View on GitHub

Popular alternatives

View all
YazSes was added to AlternativeTo by Mohsen Seyedkazemi Ardebili on and this page was last updated .
No comments or reviews, maybe you want to be first?

Official Links

AppStores & Other Links

What is YazSes?

YazSes is an open-source desktop dictation and transcription tool for Linux, macOS and Windows. Hold a key, speak, release — the text is typed straight into whatever window has focus: editor, browser, terminal or chat. After installation and the one-time model download, speech recognition runs locally on your CPU via faster-whisper, so audio and transcripts are not sent to a cloud service.

Beyond dictation it transcribes existing audio and video files to text, Markdown, SRT, WebVTT or JSON, and can capture a whole meeting hands-free and produce a speaker-labelled transcript — optionally with minutes (summary, decisions, action items) written by a local language model. Speaker names come from voiceprints you enroll yourself, stored encrypted on your own machine.

It needs no GPU, no account and no subscription, and it is Apache-2.0 licensed. Linux is the primary platform (X11 and Wayland); macOS and Windows are supported but less extensively validated on real hardware. The design and benchmarks are described in an arXiv paper.

Accessibility features include a dysfluency mode that collapses stutters and repeats for stuttered or dysarthric speech, per-user voice calibration, and an alternative activation route using a muscle (EMG) sensor for people who cannot press a key.

YazSes Videos