# How To Master Dictation in Raycast > [!question] Lingering Questions > - Where does Raycast send dictation audio, and what are the privacy implications for client or confidential work? > - How well do auto-translation Styles handle technical jargon and code terms specifically (versus the general-language examples shown)? > - Will Pro pricing (dictation moves from free-beta to Pro plan) change adoption once the beta ends? > [!tip] Article Ideas > - Try dictating a real Claude Code prompt via a Raycast Style that outputs markdown, and write up whether voice input measurably beats typing for prompt composition specifically. > [!link] Cross Reference > - [[Personal Knowledge Management MOC]] — a friction-reduction case study adjacent to the Forte context-management piece from the same batch > - [[AI & the Future of Knowledge Work MOC]] — dictating LLM prompts as a hands-free prompting workflow > [!quote] Vocabulary > - *Styles* — Raycast's context-aware transcription instructions, assignable per app/website or fired manually, each with an optional dedicated hotkey > - *global custom instructions* — dictation instructions applied to every transcription regardless of Style (accent notes, forced lowercase, etc.) ## Bib capsule A Raycast product walkthrough demonstrates the dictation feature in the Raycast 2.0 beta (macOS and now Windows), covering setup, Styles, custom vocabulary, and power-user hotkey tricks. ## Author's thesis (what is this source about / what is asserted) Dictation becomes a daily input method only once a dedicated hotkey removes the friction of triggering it, and the real leverage comes from Styles (context-aware transcription per app, translation, format-output) plus a custom vocabulary that tames accents and brand names. ## Key arguments (≤3) 1. **A dedicated hotkey is the precondition for adoption**: unlike most Raycast commands, dictation specifically benefits from a hotkey because "it's highly encouraged... so you can really leverage your muscle memory" — removing the search-and-launch step is what makes voice input reflexive. 2. **Styles let one tool serve many contexts without reconfiguration**: per-app instructions can fix proper-noun handling, auto-translate, or format output as markdown/LaTeX/IPA, firing automatically or on their own hotkey. 3. **Custom vocabulary is a low-effort, durable fix for the most common frustration**: adding a single misrecognized word (their example: "capture") permanently resolves that specific accent-driven error. ## Claim atoms ### Set a dictation hotkey so triggering becomes muscle memory > [!quote] ID:rw_pending > "it's highly encouraged to have a hotkey, so you can really leverage your muscle memory and make it second nature to just press it to dictate into any text field in any app" Where/why: [00:00:34] — dictation specifically benefits from a hotkey where most Raycast commands don't; removes the open-and-search step that stands between wanting to dictate and actually doing it. ### Styles set context-aware transcription instructions per app > [!quote] ID:rw_pending > "they basically allow you to set custom instructions for transcribing your dictations that will be used in specific contexts" Where/why: [00:02:12] — Styles auto-fire per app/website or run manually, each with optional hotkeys; can translate, format markdown, output LaTeX/IPA, or fix per-app proper names. ### Add misheard words to custom vocabulary to fix accent errors > [!quote] ID:rw_pending > "I added 'capture' as a vocab word, and now it doesn't happen anymore." Where/why: [00:07:05] — custom vocabulary is independent of Style; a concrete before/after fix for the most common dictation frustration. ## Permanent candidates - **Voice input becomes a habit only when friction drops below typing** — a strong, portable claim about tool adoption that generalizes past dictation specifically. Promoted below. ## Processing checklist - [ ] Set a Raycast dictation hotkey and add a global custom instruction for accent/casing - [ ] Create one markdown-output Style and dictate a real Claude Code prompt with it - [x] Connect into the relevant MOCs — [[3. Resources/MOCs/Personal Knowledge Management MOC]], [[3. Resources/MOCs/AI & the Future of Knowledge Work MOC]] ## Metadata - Source: [[3. Resources/Readwise/Articles/How To Master Dictation in Raycast]] ## Links - [[3. Resources/MOCs/Personal Knowledge Management MOC]] — a friction-reduction pattern adjacent to context-staging as a lever on daily AI-assisted work - [[3. Resources/MOCs/AI & the Future of Knowledge Work MOC]] — dictating prompts directly as a hands-free LLM workflow