Notes

Essays on owning your voice.

Dictation, privacy and local AI, written plainly. How speech software actually works, where your voice goes, and how to write faster without giving your words to someone else's cloud.

6 NOTES · PRIVACY / LOCAL AI / MAC PRODUCTIVITY / GUIDES / ENGINEERING

LATEST NOTES

BYOK explained: what bring your own key means for dictationBYOK lets you plug your own OpenAI, OpenRouter, Gemini or xAI API key into ShoutFlow: frontier-model clean-up, billed at cost, with no middleman in your data path.READ NOTE →Why we built ShoutFlow to run entirely on your MacModern Apple Silicon can transcribe and rewrite your speech faster than a round trip to someone else's server. The architecture behind ShoutFlow's local mode, and why private by architecture beats private by policy.READ NOTE →Cloud vs local dictation: where does your voice actually go?A plain-English map of the data path behind every dictation app: what leaves your machine, who can hear it, and the questions to ask before you install one.READ NOTE →How writers draft three times faster by dictating firstSpeaking runs at 150 words a minute; typing at 40. A practical workflow for using dictation to get the ugly first draft out of your head and onto the page, then editing like a writer.READ NOTE →The voice privacy checklist: five questions before you installBefore any dictation app gets microphone access, ask these five questions. The answers tell you whether your voice stays yours or becomes someone else's training data.READ NOTE →WhisperKit and MLX: the on-device stack behind ShoutFlowA technical tour of the two open-source projects that let ShoutFlow transcribe and clean up speech entirely on Apple Silicon, with no cloud round trip.READ NOTE →