Preview. These maps are our reading of public sources and haven't been checked with the projects' maintainers yet.
YazSes
Free, offline hold-to-talk dictation for Linux (primary), macOS and Windows using faster-whisper on the CPU, with meeting capture and speaker labels.
v2.46.0 released 2026-10-24; last push 2026-10-26 (gh api). Very frequent releases. (checked 2026-10-25)
In Voice dictation apps
Where it stands apart
- How is it mainly sustained? individual side project, no revenue (24% of 21 others)
- Who is it for? both (19% of 21 others)
- Which open speech models can it run on your device? one model family (e.g. only Whisper) (18% of 17 others)
- Does it use an AI model to clean up or rewrite your dictated text, and where does that run? AI rewrite on your device only (10% of 21 others)
- If you use cloud speech or AI, how is it paid for? no cloud option (19% of 21 others)
- Where does it run? several desktop systems (24% of 21 others)
What it shares with most of the community
- Is it actively maintained? active (100% of 21 others)
- Can it run entirely on your own device or infrastructure, without the maker's servers? yes (57% of 21 others)
- Do you need an account to use it? no account (68% of 19 others)
- Where does speech recognition happen by default? on your device by default (65% of 20 others)
Nearest neighbors
- TuxWhisper 87% of 15 shared answers match
- Dictata 73% of 15 shared answers match
- Qwen Scribe 73% of 15 shared answers match
Every answer
| Question | Answer | Source |
|---|---|---|
| Is it actively maintained? | active | source 2026-10-26 |
| How is the main thing licensed? | permissive open source (MIT/Apache/BSD) | source 2026-10-26 |
| How is it mainly sustained? | stands apart individual side project, no revenue | source 2026-10-26 |
| Can it run entirely on your own device or infrastructure, without the maker's servers? | yes | source 2026-10-26 |
| Do you need an account to use it? | no account | source 2026-10-26 |
| Who is it for? | stands apart both Targets privacy-conscious professionals and people with motor disabilities, but Linux setup needs input-group and ydotool steps. | source 2026-10-26 |
| Which shared standard or format does it mainly build on? | OpenAI Whisper models (whisper.cpp, faster-whisper, WhisperKit) faster-whisper on CPU. | source 2026-10-26 |
| Where does speech recognition happen by default? | on your device by default | source 2026-10-26 |
| Which open speech models can it run on your device? | stands apart one model family (e.g. only Whisper) | source 2026-10-26 |
| Does it use an AI model to clean up or rewrite your dictated text, and where does that run? | stands apart AI rewrite on your device only Optional small offline LLM for grammar, off by default. | source 2026-10-26 |
| If you use cloud speech or AI, how is it paid for? | stands apart no cloud option | source 2026-10-26 |
| What is the main way users pay the maker? | nothing | source 2026-10-26 |
| Where does it run? | stands apart several desktop systems Linux is primary; macOS and Windows builds are labelled preview. | source 2026-10-26 |
| Does it also record meetings or calls? | yes | source 2026-10-26 |
| Is 'your voice never leaves your device' the headline promise? | yes, it is the main promise | source 2026-10-26 |
Sources
This page was derived from:
- GitHub · github.com/MSKazemi/yazses · read 2026-10-25
RSS for this project · Its own release feed
Are you a maintainer? Claiming and correcting projects is coming soon.