optionOS optionOS

The voice task flow end to end: speak, mark, merge, hand to the agent

How do I use it?
EditorClaude Fable 5
Tags
  • WORKFLOWRepeatable working flow.
  • VOICEVoice-driven production.
  • FEATUREVisible app capability.
  • ACTIVE-USECurrently in use.

Every screen relates to the others; this page merges them into one structure. The flow below is not separate images: it is a single journey that tells what a person does from start to finish, with the screens linked to each other. Open your terminal, start the speech with ⌥A and walk the flow click by click.

Desktop with terminals, the capture menu, the speech watch bar and paste targets Capture menuSpeech watch barSpeech contextWaveformBackground transcriptionCopied itemsToken estimateCopied contentType sent to the agentCapture actionsCollapse the menuCapture ScreenRecord GIFPaste into ClaudePaste into Codex
·
Start

The moment speech opens, this menu comes to you; the whole journey starts here.

Open your terminal or Ghostty, start the speech with ⌥A: the capture menu appears.
11 screens in one flow: start the speech, watch, copy, record a GIF, finish, preview, merge, edit and paste to the agent.

The last step of every screen is the door to the next: click or hover the door region and you step into the picture inside the picture.

Small notes that live inside the flow: there is also a cursor follower — while speaking you see the recording state next to your cursor; no photo needed, you will run into it. Content is copied as it is pulled; the photos and clipboard update inside the speech as you copy, and the system sees it all as one session.

Your whole speech archive lives at ⌥H. The Dictation History panel collects your speeches on one searchable, tagged, starred and badged surface; since audio is saved every time, no speech is lost even if the app breaks. The second flow below walks that panel end to end.

Dictation History panel: search, live-updating speech, tags, star and the badge popover SearchSpeech contentsLive-updating speechTagSpeech durationRelation groupLink markStarSuggestionsLinked speechesRemoved hallucinationAction badgeRectangle badgeRectangle badge — rightObject badgeBadge example — bottomBadge example — middleBadge example — topBadge popover
·
Panel

Search across your speeches; your latest recording updates live in the list.

⌥H opens Dictation History: all your speeches on one panel.
From ⌥H to the audio bar: search, star-versus-tag, badges, multi-select, including, recording safety and listening from text.

The badge in the panel and the badge in the speech are the same badge; the system works coherently.

The trick for not losing yourself in a long speech: make it count. I have the AI enumerate the tasks — so my own speech is not forgotten. At the end it hands everything back in one pass. When I paste the output I also make the agent tell me what it understood; every round sharpens itself. The pattern I use:

> Enumerate every task as [n/m] and proceed; change the counter when the goal changes. At the end, hand everything back to me in one pass.