Preview. These maps are our reading of public sources and haven't been checked with the projects' maintainers yet.
Sayso
Free, GPL-licensed dictation app for macOS, Windows and Linux that runs Parakeet, Whisper and many other models locally, with optional AI 'styles'.
github.com/watzon/saysoActive
v0.11.0 released 2026-10-23; last push 2026-10-24 (gh api). (checked 2026-10-25)
In Voice dictation apps
Where it stands apart
- How is the main thing licensed? copyleft or source-available with restrictions (5% of 21 others)
- Which shared standard or format does it mainly build on? NVIDIA Parakeet models (17% of 18 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)
- Who is it for? non-developers (76% of 21 others)
- Where does speech recognition happen by default? on your device by default (65% of 20 others)
- Which open speech models can it run on your device? several model families (e.g. Whisper and Parakeet) (53% of 17 others)
- Does it also record meetings or calls? no (52% of 21 others)
Nearest neighbors
- Handy 93% of 15 shared answers match
- BetterWispr 73% of 15 shared answers match
- SpeakoFlow 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? | stands apart copyleft or source-available with restrictions GPL-3.0. | source 2026-10-26 |
| How is it mainly sustained? | individual with revenue (paid app, tier, ads, or donations) Solo maker with a GitHub Sponsors badge. | 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? | non-developers | source 2026-10-26 |
| Which shared standard or format does it mainly build on? | stands apart NVIDIA Parakeet models 'The default, Parakeet Unified'. | 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? | several model families (e.g. Whisper and Parakeet) | source 2026-10-26 |
| Does it use an AI model to clean up or rewrite your dictated text, and where does that run? | AI rewrite on device or in the cloud, your choice Styles call any OpenAI-compatible endpoint (local or cloud) or the Claude/Codex CLI; Raw is the default. | source 2026-10-26 |
| If you use cloud speech or AI, how is it paid for? | only with your own API key (you pay the provider) Cloud speech via your own OpenAI, Groq, ElevenLabs, Deepgram, AssemblyAI or Mistral key. | 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 | source 2026-10-26 |
| Does it also record meetings or calls? | no | 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/watzon/sayso · read 2026-10-25
RSS for this project · Its own release feed
Are you a maintainer? Claiming and correcting projects is coming soon.