# From ⌥A to close: everything a voice session collects while you talk

> This guide was produced with the very method it describes: one 12-minute spoken session, rectangles drawn while talking, and captures taken along the way.…

Canonical: https://optionos.app/guide/en/voice-session-walkthrough
Published: 2026-07-14
Source: optionos-product:r19

This guide was produced with the very method it describes: one 12-minute spoken session, rectangles drawn while talking, and captures taken along the way. Every visual below is interactive — hover or click the numbered targets and the explanation opens next to the target.

![The 12-minute recording that produced this guide, shown in the transcript panel](https://optionos.app/guide/voice-session-cover.png)
*Everything on this page was captured in a single 12-minute conversation; transcript, marks and visuals share one timeline.*
Interactive scene: https://optionos.app/guide/en/voice-session-walkthrough#voice-session-cover

Start recording with ⌥A. The recording bar appears with the Capture Actions menu next to it; while you talk, everything is collected with timestamps.

![optionOS recording bar and Capture Actions menu](https://optionos.app/guide/voice-session-capture-menu.png)
*While recording, every capture action lives in one menu, each with its shortcut.*
Interactive scene: https://optionos.app/guide/en/voice-session-walkthrough#voice-session-capture-menu

Capture a screen region when you need to show something visual; the capture lands in the conversation queue — hover for a preview, click to edit.

![Preview and edit area of content captured into the conversation](https://optionos.app/guide/voice-session-conversation-preview.png)
*Hover: preview. Click: edit. The bar below shows which agent and voice profile you are talking to.*
Interactive scene: https://optionos.app/guide/en/voice-session-walkthrough#voice-session-conversation-preview

In the editor the rectangle tool comes pre-selected: say "this part needs fixing", draw a rectangle, and the pause matches the drawing to that exact moment of speech.

![Annotation toolbar: rectangle, number and undo](https://optionos.app/guide/voice-session-annotation-editor.png)
*Draw rectangles, drop numbers if you prefer; remove a wrong mark by tapping it or with ⌘Z.*
Interactive scene: https://optionos.app/guide/en/voice-session-walkthrough#voice-session-annotation-editor

![Drawing and image references in a transcript line](https://optionos.app/guide/voice-session-transcript-references.png)
*References embed into the flow of speech; a rectangle chip binds to the moment it was drawn, an image chip to the original file.*
Interactive scene: https://optionos.app/guide/en/voice-session-walkthrough#voice-session-transcript-references

Add Note attaches typed text to that moment of the conversation — use it sparingly, for proper nouns and words the transcriber gets wrong.

![Add Note panel open](https://optionos.app/guide/voice-session-note-panel.png)
*For special words only; Enter attaches the note.*
Interactive scene: https://optionos.app/guide/en/voice-session-walkthrough#voice-session-note-panel

Use Get Text to pull text straight out of an image, and Record Screen to show anything that moves.

![Screen recording panel over the selected region](https://optionos.app/guide/voice-session-screen-recording.png)
*The selected region is recorded; Stop finishes, Cancel discards.*
Interactive scene: https://optionos.app/guide/en/voice-session-walkthrough#voice-session-screen-recording

![A short screen recording of an agent working](https://optionos.app/guide/voice-session-screen-recording-example.gif)
*The original MP4 is stored for playback; the agent receives a derived frame digest by default.*

![Changed-region frames of the screen recording in the panel](https://optionos.app/guide/voice-session-screen-recording-frames.png)
*Only changed regions become frames — moving objects and changing text are captured one by one.*
Interactive scene: https://optionos.app/guide/en/voice-session-walkthrough#voice-session-screen-recording-frames

![video preview and format selector](https://optionos.app/guide/voice-session-screen-recording-preview.png)
*Watch the screen recording to verify; switch what the agent receives from the selector.*
Interactive scene: https://optionos.app/guide/en/voice-session-walkthrough#voice-session-screen-recording-preview

For time-based work, the Speech Context menu marks a start flag (press again to close the range) and Speech Source hands the agent the fully timestamped transcript — it finds the exact second you said "I clicked this and that happened".

![Speech Context menu with start marking and speech source](https://optionos.app/guide/voice-session-speech-context-menu.png)
*Your speech is data; flags define ranges, the source carries exact time.*
Interactive scene: https://optionos.app/guide/en/voice-session-walkthrough#voice-session-speech-context-menu

![Scrolling Capture under Special Capture](https://optionos.app/guide/voice-session-scrolling-capture.png)
*A long page becomes one tall image instead of two or three fragments.*
Interactive scene: https://optionos.app/guide/en/voice-session-walkthrough#voice-session-scrolling-capture

It is all one flow: start with ⌥A, talk, mark what you see, capture motion with a screen recording, text as text, special words as notes. When the session ends, the agent holds your speech, marks and visuals merged on a single timeline.