#51 · Primary category: Speech & Audio

openless

ai-prompt asr dictation linux llm macos open-source prompt-engineering rust speech-to-text tauri typeless typeless-alternative voice-input windows wispr-flow-alternative

Hold a key, speak, release — AI-polished text appears at your cursor in any app. Open-source voice input for macOS & Windows.

Project last updated:08/27/26

GitHub Stars

3.4K

Forks

298

Contributors

50

License

MIT

Why we included this project

Most dictation tools hand you a raw transcript and call it done. OpenLess instead cleans the speech up as it goes: press and hold a hotkey, talk, and the polished, structured version of what you said lands at the cursor in whatever app you're using. Its AI-prompt mode takes rambling notes and reshapes them into a prompt you can paste straight into ChatGPT, Claude, or Cursor. Around that it handles the usual friction: custom style packs to match your writing voice, a dictionary that learns proper nouns and corrections, and streaming insertion with clipboard fallback for apps that block keystrokes. It runs locally on macOS and Windows with bring-your-own ASR and polish providers, so you aren't tied to one vendor. If you dictate emails, messages, or meeting notes and want readable output instead of verbatim speech, this is worth trying.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category