About & license

Row	What it gives you
Version	The build you are running.
Check for updates	A manual check, the same one the tray item runs. Disabled if you turned automatic update checks off in Settings → General, which are on by default.
App language	The language of the SpeakoFlow interface.
Source code, License	Links to the repository and the license file.
Folders	Your app data folder (models, history, settings) and your log directory, each with a button to open it.

Row

What it gives you

Version

The build you are running.

Check for updates

A manual check, the same one the tray item runs. Disabled if you turned automatic update checks off in Settings → General, which are on by default.

App language

The language of the SpeakoFlow interface.

Source code, License

Links to the repository and the license file.

Folders

Your app data folder (models, history, settings) and your log directory, each with a button to open it.

Known limitations

macOS builds are Apple Silicon only. GitHub retired its Intel build machines in December 2025, so there is currently no way to produce and test an Intel build. Intel Mac users can build from source.

There is no Linux .rpm. The packaging does not bundle the speech engine correctly, and shipping an .rpm that installs but cannot transcribe would be worse than shipping none. Fedora and openSUSE users should use the AppImage.

Builds are not code signed yet. On macOS that means one Terminal command on first install. On Windows, SmartScreen may warn you the first time you run the installer.

Unsigned builds cannot auto-update on macOS. Updating means downloading the new .dmg and repeating the one-time command.

The release pipeline is already wired for signing. It needs the paid Apple Developer membership and a Windows certificate. Steps for the macOS command are in Install.

Roadmap

Code signing for Windows and macOS

A wider model catalog and more one-click local models

More community translations

Voice-to-text tuned for agentic coding

Prompt-engineering help: describe what you want to build and get a solid prompt back

Voice commands: trigger actions and complete tasks by voice

License and credits

SpeakoFlow is open source under the MIT License.

Its dictation core comes from Handy by CJ Pais, used under the MIT license. The Whisper and Parakeet pipeline, VAD, overlay, and settings architecture all trace back to that project. Thanks to CJ for making it open.

The assistant, screen vision, Generate with Flow, translation, text-to-speech, and memory layers are SpeakoFlow’s own. Thanks also to Tauri, whisper.cpp, llama.cpp, Silero VAD, and Kokoro.

Tech stack

Layer	What it uses
App	Tauri 2, with a Rust backend and a React and TypeScript frontend.
Speech-to-text	whisper.cpp and Parakeet with GPU acceleration, plus Silero VAD for voice detection.
Assistant	A built-in llama.cpp engine, or any OpenAI-compatible provider you configure.
Text-to-speech	Kokoro locally, with OpenAI-compatible, ElevenLabs, and Azure options.

Have an idea, or hit a bug not covered here? Open an issue or browse the repository.

Accuracy

Models

Settings

Help

Known limitations

Roadmap

License and credits

​Known limitations

​Roadmap

​License and credits

Known limitations

Roadmap

License and credits