Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 21 additions & 0 deletions app/docs/interact/web-ui/page.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -184,6 +184,27 @@ Paste images, screenshots, diagrams, and mockups directly into the conversation.
Omnigent sees them alongside your text. Useful for frontend work where describing a layout
issue in words is slower than screenshotting it.

## Voice dictation

Dictate into the composer instead of typing. Click the **Voice dictation** mic
button next to the composer, speak, and the transcript streams into the input as
you go. Where the browser exposes Web Speech (Chrome, Safari) it's used directly;
otherwise — and always in the desktop app — dictation runs through the server.

You can also toggle dictation from the keyboard with `⌘⌥V` (`Ctrl+Alt+V` on
Windows and Linux) — the same action as clicking the mic, reachable from anywhere
in the app so you can start and stop talking without leaving the keyboard. The
chord is inert when focus is inside a terminal or the code editor, which own
their own keys. It's listed in the keyboard-shortcuts reference (`⌘/`) as
`Toggle voice dictation`.

While dictation is listening, two keys end the take:

- **Enter** stops dictation and keeps the dictated text in the composer (it is
not sent).
- **Esc** stops dictation and discards it, reverting the composer to whatever it
held before you started talking.

## Message queue and steering

Type a follow-up while the agent is still working and it's held in a client-side
Expand Down
Loading